© 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. 27937
    Prev
    Next
    INDEX
    Explanations

    Earth Day, Groupon, design, globalization

    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
    аве
    -0.07
     grop
    -0.07
    že
    -0.06
    ampo
    -0.06
    èĢ½
    -0.06
    è¿Ļ个æĺ¯
    -0.06
    igna
    -0.06
    êµ´
    -0.06
    å¤ľæ·±
    -0.06
    feu
    -0.06
    POSITIVE LOGITS
    Ĵ·
    0.08
    θεν
    0.08
    表çİ°åľ¨
    0.07
    pcf
    0.07
    omm
    0.07
    IVI
    0.07
    ×Ĺ×Ļ×Ŀ
    0.07
    offsetof
    0.07
    odos
    0.07
    iliar
    0.07
    Activations Density 0.020%

    No Known Activations