© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 23753
    Prev
    Next
    INDEX
    Explanations

    security

    np_max-act · gemini-2.0-flash

    Tokens related to computer/security topics — discussions of security measures, risks, protections, and best practices.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    方方面面
    -0.08
    桥梁
    -0.07
     TN
    -0.07
    TV
    -0.07
     ModelRenderer
    -0.07
     Tx
    -0.07
     KS
    -0.07
     campaña
    -0.07
    posición
    -0.06
     anne
    -0.06
    POSITIVE LOGITS
     Reuters
    0.08
     применя
    0.07
    upro
    0.07
     ################################################################
    0.06
    ปลาย
    0.06
    _REFERER
    0.06
    _WAKE
    0.06
    _Dis
    0.06
    .Address
    0.06
    <\/
    0.06
    Activations Density 0.145%

    No Known Activations