© 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. 119196
    Prev
    Next
    INDEX
    Explanations

    bird descriptions

    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
    旰
    -0.09
    Listen
    -0.07
     woo
    -0.07
     alleg
    -0.07
     Break
    -0.07
     backstage
    -0.07
    _cou
    -0.07
    RenderWindow
    -0.07
    薪资
    -0.07
     enlight
    -0.07
    POSITIVE LOGITS
    硬件
    0.07
    .UndefOr
    0.07
    _)
    0.07
    햏
    0.07
     GLenum
    0.07
     adoption
    0.07
     recommendations
    0.07
    〉
    0.07
     president
    0.07
    )">↵
    0.07
    Activations Density 0.017%

    No Known Activations