© 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. 60262
    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
    -states
    -0.08
    胎
    -0.07
     genomic
    -0.06
    Rectangle
    -0.06
    -abs
    -0.06
     Smoke
    -0.06
     wis
    -0.06
    充
    -0.06
    ordinate
    -0.06
    Smoke
    -0.06
    POSITIVE LOGITS
    สวน
    0.07
    LOT
    0.07
     ajud
    0.07
    ┏
    0.07
     Adelaide
    0.07
    思い出
    0.07
    ቤ
    0.07
     طبيعي
    0.07
     FW
    0.07
    公诉
    0.07
    Activations Density 0.054%

    No Known Activations