© 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. 9947
    Prev
    Next
    INDEX
    Explanations

    copy of

    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
    ä¸ĵ家表示
    -0.08
    ä¸ĵ家ä»ĭç»į
    -0.08
    uille
    -0.08
    lexport
    -0.08
    [src
    -0.08
    -spe
    -0.07
    æļĩ
    -0.07
    aleza
    -0.07
    udev
    -0.07
    xdc
    -0.07
    POSITIVE LOGITS
    被ç½ļ
    0.07
    鸥
    0.06
     reda
    0.06
    æĦģ
    0.06
    éĢļè¿ĩå°Ĩ
    0.06
    ç«¥åŃIJ
    0.06
    0.06
    Typed
    0.06
    arent
    0.06
    æ²ī
    0.06
    Activations Density 0.512%

    No Known Activations