© 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. 8402
    Prev
    Next
    INDEX
    Explanations

    brackets

    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
    Clinton
    -0.07
    东风
    -0.07
    _fu
    -0.07
    ﮢ
    -0.06
    赇
    -0.06
     önü
    -0.06
    簉
    -0.06
     Endpoint
    -0.06
     Klaus
    -0.06
    𬶮
    -0.06
    POSITIVE LOGITS
    Et
    0.08
    Price
    0.07
     сост
    0.07
    สวย
    0.07
    ismic
    0.07
    preferred
    0.07
    જ
    0.07
     Muj
    0.07
    ([]);↵
    0.06
    Settings
    0.06
    Activations Density 0.005%

    No Known Activations