© 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. 45498
    Prev
    Next
    INDEX
    Explanations

    coding examples and documentation

    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
    æĪijå¾Īåĸľæ¬¢
    -0.10
    ’B
    -0.08
    ĮĢ
    -0.08
    _mtx
    -0.07
    çī§ç¾Ĭ
    -0.07
    åĽłä¸ºæĺ¯
    -0.07
    åIJĥäºĨä¸Ģ
    -0.07
    istol
    -0.07
    _handlers
    -0.07
    anth
    -0.07
    POSITIVE LOGITS
    åıĭæĥħ
    0.06
    ża
    0.06
    æ´Ľæĸ¯
    0.06
    odin
    0.06
    è²´
    0.06
     (**
    0.06
    odz
    0.06
    ç´¹
    0.06
    輸åħ¥
    0.06
     redis
    0.06
    Activations Density 0.002%

    No Known Activations