© 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. 59938
    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
    老人家
    -0.08
     panorama
    -0.08
    澜
    -0.08
     Braz
    -0.07
    村民
    -0.07
     mümkün
    -0.07
    roid
    -0.07
    良性
    -0.07
    王朝
    -0.07
     brave
    -0.07
    POSITIVE LOGITS
    ninger
    0.07
    SETTING
    0.07
    OUNTER
    0.07
    HF
    0.07
     anticipating
    0.06
     tips
    0.06
     отзыв
    0.06
    CPU
    0.06
     ){
    0.06
     تح
    0.06
    Activations Density 0.002%

    No Known Activations