© 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. 15-RESID-POST-AA
    11. 80163
    Prev
    Next
    INDEX
    Explanations

    from

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     negotiate
    -0.07
    :<
    -0.07
    做的
    -0.07
    atient
    -0.07
     Commissioner
    -0.06
     nối
    -0.06
    ollapsed
    -0.06
     forward
    -0.06
     "|
    -0.06
    .ham
    -0.06
    POSITIVE LOGITS
    <IActionResult
    0.07
     COPYRIGHT
    0.07
    时效
    0.07
    基调
    0.07
    dana
    0.07
     disposing
    0.07
    .AnchorStyles
    0.07
    ANA
    0.07
    끗
    0.07
    FIELD
    0.07
    Activations Density 0.102%

    No Known Activations