© 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. 15-RESID-POST-AA
    11. 118152
    Prev
    Next
    INDEX
    Explanations

    censored/uncensored

    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_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
     validators
    -0.08
    _sigma
    -0.07
    وض
    -0.07
    矢
    -0.07
     unresolved
    -0.07
    Concept
    -0.07
    建造
    -0.07
     scaleFactor
    -0.07
    武器
    -0.07
    .navigateTo
    -0.07
    POSITIVE LOGITS
     zipper
    0.07
    槚
    0.07
    玞
    0.07
    "}},↵
    0.07
    推送
    0.07
    logged
    0.06
    ıc
    0.06
    �
    0.06
     chicas
    0.06
    _paths
    0.06
    Activations Density 0.011%

    No Known Activations