© 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. 58356
    Prev
    Next
    INDEX
    Explanations

    percentage values

    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
    好æĸĩ
    -0.09
    fav
    -0.07
     Feliz
    -0.07
    cov
    -0.07
    semb
    -0.07
    æĻ®äº¬
    -0.07
    ÑĪÑĤа
    -0.07
    iedades
    -0.07
    åģ¥ç¾İ
    -0.07
     зак
    -0.07
    POSITIVE LOGITS
    ìĸ´ëĵľ
    0.07
    Æ°á»Ľc
    0.07
     Sheridan
    0.06
    ackbar
    0.06
     /*
    0.06
    åıį
    0.06
     Activ
    0.06
     Sight
    0.06
    edly
    0.06
    οÏħÏĥ
    0.06
    Activations Density 0.024%

    No Known Activations