© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25925
    Prev
    Next
    INDEX
    Explanations

    all or everything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verk
    -0.08
     anything
    -0.08
    anything
    -0.08
    ews
    -0.08
    fer
    -0.07
    bauer
    -0.07
     amongst
    -0.07
     elsewhere
    -0.07
    otto
    -0.07
    stituto
    -0.06
    POSITIVE LOGITS
    æĪĸéĥ¨åĪĨ
    0.10
    /all
    0.09
    ä¸Ģèµ·
    0.07
     ÑĢазом
    0.07
     sekaligus
    0.07
    aylor
    0.07
    åľ¨åĨħçļĦ
    0.07
    ä¸Ģèµ·æĿ¥
    0.07
    äºĨä¸Ģéģį
    0.07
    ĸ
    0.07
    Activations Density 0.090%

    No Known Activations