© 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. 79957
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     migraine
    -0.08
    (Android
    -0.07
    总产值
    -0.07
    tą
    -0.07
     edu
    -0.07
     bored
    -0.07
     genre
    -0.06
     stair
    -0.06
     surre
    -0.06
    atisf
    -0.06
    POSITIVE LOGITS
    失控
    0.07
     автомат
    0.07
    .Release
    0.07
     */,↵
    0.07
     filming
    0.07
    PEC
    0.06
    所以我们
    0.06
    scalar
    0.06
     surrounding
    0.06
     Click
    0.06
    Activations Density 0.032%

    No Known Activations