© 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. 11-RESID-POST-AA
    11. 108214
    Prev
    Next
    INDEX
    Explanations

    court appeals

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ensl
    -0.09
     thieves
    -0.07
     indispensable
    -0.07
    舒心
    -0.07
     murdered
    -0.07
     Invent
    -0.07
     merch
    -0.07
    Effective
    -0.07
     Choosing
    -0.07
     Sie
    -0.07
    POSITIVE LOGITS
     runes
    0.08
     websocket
    0.07
     TEMP
    0.07
    ☍
    0.07
     SMP
    0.07
     fluctuations
    0.07
    优化
    0.07
    回归
    0.07
    瑁
    0.07
    верх
    0.07
    Activations Density 0.003%

    No Known Activations