© 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. 21337
    Prev
    Next
    INDEX
    Explanations

    global reputation

    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
    afia
    -0.07
    éĹ´æİ¥
    -0.07
    ..."
    -0.07
    .struct
    -0.06
    è¯¥ä½ľèĢħ
    -0.06
    æĺ¯åIJ§
    -0.06
    _sleep
    -0.06
    ...,
    -0.06
     Catch
    -0.06
    带åħ¥
    -0.06
    POSITIVE LOGITS
    ä½łçŁ¥éģĵåIJĹ
    0.07
    äle
    0.07
     itemType
    0.07
    rones
    0.07
    ä¸ĭæīĭ
    0.07
    иж
    0.07
    INGTON
    0.07
    ETTE
    0.07
    ittää
    0.07
    __$
    0.07
    Activations Density 0.010%

    No Known Activations