© 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. 15725
    Prev
    Next
    INDEX
    Explanations

    code examples

    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
    .baidu
    -0.07
    ä¸įå·²
    -0.07
     ken
    -0.07
    æ·¹
    -0.07
    æĮĸæİĺåħ¬åı¸
    -0.06
    _VIRTUAL
    -0.06
    ÂŃ
    -0.06
    ÐłÐĿ
    -0.06
    ÙĪÙĦÙĬÙĨ
    -0.06
    çĶŁäº§æĬĢæľ¯
    -0.06
    POSITIVE LOGITS
    åIJīæĸ¯
    0.07
    asic
    0.07
    olu
    0.07
    REAK
    0.07
    lu
    0.07
    кÑĬ
    0.06
    åĤĻ
    0.06
    azes
    0.06
    ream
    0.06
    çļĦä¿¡å¿ĥ
    0.06
    Activations Density 0.015%

    No Known Activations