© 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. 19-RESID-POST-AA
    11. 71175
    Prev
    Next
    INDEX
    Explanations

    disputes claims

    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
    china
    -0.08
     Tyler
    -0.07
    想知道
    -0.07
    \Desktop
    -0.07
    Tyler
    -0.07
    .MapPath
    -0.07
     australia
    -0.07
     Mueller
    -0.07
     kf
    -0.07
     workstation
    -0.07
    POSITIVE LOGITS
     sum
    0.07
     Composite
    0.07
    דמי
    0.07
    Som
    0.07
    _sum
    0.07
    灯光
    0.07
    🤰
    0.07
    �
    0.06
     Twice
    0.06
    _NOT
    0.06
    Activations Density 0.041%

    No Known Activations