© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 8949
    Prev
    Next
    INDEX
    Explanations

    that

    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
    Soon
    -0.07
     situ
    -0.07
    .atan
    -0.07
    erre
    -0.06
    nation
    -0.06
    חבורה
    -0.06
     På
    -0.06
    esa
    -0.06
    حلم
    -0.06
    linear
    -0.06
    POSITIVE LOGITS
    台南
    0.07
    						
    0.07
     Mitsubishi
    0.07
    への
    0.06
    \Contracts
    0.06
    苡
    0.06
    PrototypeOf
    0.06
    DJ
    0.06
    _DETECT
    0.06
    ypass
    0.06
    Activations Density 0.048%

    No Known Activations