© 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. 30323
    Prev
    Next
    INDEX
    Explanations

    testing frameworks

    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
     dispon
    -0.08
     person
    -0.07
    Signed
    -0.07
    ｻ
    -0.07
    Thank
    -0.07
    𝙪
    -0.07
    外观
    -0.07
    _Ex
    -0.07
    的表情
    -0.06
    .drawImage
    -0.06
    POSITIVE LOGITS
    kaar
    0.07
     scal
    0.07
    Making
    0.06
    开荒
    0.06
    八字
    0.06
    نهار
    0.06
     stacks
    0.06
    .radians
    0.06
     rat
    0.06
    ROY
    0.06
    Activations Density 0.008%

    No Known Activations