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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4284
    Prev
    Next
    INDEX
    Explanations

    Formal/technical language

    np_max-act · gemini-2.0-flash
    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
     pasa
    -0.07
    _RST
    -0.07
    .cpu
    -0.07
    ꕥ
    -0.07
    _inp
    -0.07
    vpn
    -0.07
    처리
    -0.07
    抱怨
    -0.06
     cazzo
    -0.06
     grou
    -0.06
    POSITIVE LOGITS
     secure
    0.07
    清晰
    0.07
    –
    0.07
    公司在
    0.07
     -
    0.06
     testCase
    0.06
    ：
    0.06
    -
    0.06
    做了
    0.06
    arent
    0.06
    Activations Density 0.863%

    No Known Activations