© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 18062
    Prev
    Next
    INDEX
    Explanations

    kidney

    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
     bees
    -0.07
     Phen
    -0.07
     rè
    -0.07
    /licenses
    -0.07
     supervise
    -0.07
     për
    -0.07
     possui
    -0.07
     locate
    -0.07
    的语言
    -0.07
    @yahoo
    -0.07
    POSITIVE LOGITS
    _NOTIFY
    0.07
    ulis
    0.06
    _symbols
    0.06
    ansi
    0.06
    致癌
    0.06
     FName
    0.06
     GLUT
    0.06
     ='
    0.06
    si
    0.06
    -self
    0.06
    Activations Density 0.061%

    No Known Activations