© 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 EvalsExportsAPI 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. 77080
    Prev
    Next
    INDEX
    Explanations

    Abbreviations or initials

    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
    -Javadoc
    -0.07
    ib
    -0.07
     miłości
    -0.07
    以上
    -0.06
    㐂
    -0.06
    鞲
    -0.06
    躇
    -0.06
    \\\\
    -0.06
    公斤
    -0.06
     claim
    -0.06
    POSITIVE LOGITS
    ète
    0.07
    品牌形象
    0.07
    .Append
    0.07
     Neighborhood
    0.07
    breaking
    0.07
     IEntity
    0.07
    [frame
    0.07
     LeBron
    0.07
    .Art
    0.07
    數據
    0.07
    Activations Density 0.045%

    No Known Activations