© 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. 10122
    Prev
    Next
    INDEX
    Explanations

    future diving

    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
    ìŀĸìķĦìļĶ
    -0.07
    åħ¶ä¸İ
    -0.07
    æĪĸä¸į
    -0.07
    åħ¶ä¸º
    -0.07
    åħ¶æīĢ
    -0.07
     ÙĪØ°ÙĦÙĥ
    -0.07
    çħ§æł·
    -0.07
    çŃī缸åħ³
    -0.07
    shader
    -0.07
    ç½Ĺæĭī
    -0.06
    POSITIVE LOGITS
     ìŀĪìľ¼ë©°
    0.07
     ìħĪ
    0.07
     обаÑĩе
    0.07
     wiÄĻc
    0.07
    íķĺìĺĢìľ¼ë©°
    0.07
    ì£ł
    0.07
    éĽ
    0.07
    구ìļĶ
    0.07
    ëIJĺë©°
    0.07
    strup
    0.06
    Activations Density 0.795%

    No Known Activations