© 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. 19-RESID-POST-AA
    11. 1927
    Prev
    Next
    INDEX
    Explanations

    http

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     emotions
    -0.07
    uppet
    -0.07
    长长的
    -0.07
    conversation
    -0.07
    issions
    -0.07
    nova
    -0.06
    amation
    -0.06
    𝙝
    -0.06
     amendment
    -0.06
    一條
    -0.06
    POSITIVE LOGITS
     subscribe
    0.08
     Disclosure
    0.07
     上
    0.07
    审美
    0.06
     Brom
    0.06
    hin
    0.06
     Destructor
    0.06
    _LOW
    0.06
     subconscious
    0.06
     стандарт
    0.06
    Activations Density 0.002%

    No Known Activations