© 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. 29294
    Prev
    Next
    INDEX
    Explanations

    same result or outcome

    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
    åŁºç¡ĢçļĦ
    -0.08
    _logical
    -0.07
    :[[
    -0.07
    大纲
    -0.07
    好çİ©
    -0.07
     PRIM
    -0.07
    éĢĢä¼įåĨĽäºº
    -0.07
    .foundation
    -0.07
    eof
    -0.07
    让çĶŁæ´»
    -0.07
    POSITIVE LOGITS
    igli
    0.07
     anyway
    0.07
    etch
    0.07
    繫
    0.07
    éĴ°
    0.06
    isch
    0.06
    phinx
    0.06
    ç´§è¦ģ
    0.06
    æľĢç»Īè¿ĺæĺ¯
    0.06
     unaffected
    0.06
    Activations Density 0.006%

    No Known Activations