© 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. 43565
    Prev
    Next
    INDEX
    Explanations

    programming keywords and functions

    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
    ugd
    -0.08
    enegro
    -0.08
     Tej
    -0.08
    engel
    -0.08
    åĺĪ
    -0.07
    edel
    -0.07
    ivar
    -0.07
    IGO
    -0.07
    为人æ°ijæľįåĬ¡
    -0.07
    æĸ¯é¡¿
    -0.07
    POSITIVE LOGITS
    éĩį
    0.07
    çĿĢæĪij们çļĦ
    0.07
     above
    0.06
    ooled
    0.06
    plib
    0.06
    ä¸Ĭè¿°
    0.06
    æĪij们éĥ½æĺ¯
    0.06
    ud
    0.06
    dorf
    0.06
    çĿĢæĪij们
    0.06
    Activations Density 0.024%

    No Known Activations