© 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. 73801
    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
    人间
    -0.08
    (nameof
    -0.07
    ⚙
    -0.07
    🛒
    -0.06
     Sü
    -0.06
     kol
    -0.06
     mankind
    -0.06
    (SS
    -0.06
    (models
    -0.06
    (db
    -0.06
    POSITIVE LOGITS
    的程度
    0.07
    ynomial
    0.07
     реж
    0.07
     Guides
    0.07
     legality
    0.06
     pewności
    0.06
    atég
    0.06
    何况
    0.06
     COUNT
    0.06
     FX
    0.06
    Activations Density 0.001%

    No Known Activations