© 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. 1298
    Prev
    Next
    INDEX
    Explanations

    Zea mays

    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
    putc
    -0.06
    minen
    -0.06
    ers
    -0.06
    put
    -0.06
    ç»ķ
    -0.06
    raub
    -0.06
    champ
    -0.06
     Wirk
    -0.06
    anic
    -0.06
    hers
    -0.06
    POSITIVE LOGITS
    æĸ°åĬłåĿ¡
    0.11
    åĬłæĭ¿å¤§
    0.08
    身临åħ¶å¢ĥ
    0.08
    éĺ¿æĭī伯
    0.08
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.08
    çijŀæĭī
    0.08
    azah
    0.08
    <\/
    0.08
    两åѦä¸Ģåģļ
    0.08
    Ïĥμα
    0.08
    Activations Density 0.622%

    No Known Activations