© 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. 38063
    Prev
    Next
    INDEX
    Explanations

    description/parameters

    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
    lings
    -0.08
    iento
    -0.07
    Įĵ
    -0.07
    инÑĥ
    -0.07
    üt
    -0.07
    esses
    -0.07
    utos
    -0.07
    Ł
    -0.07
    ectomy
    -0.07
    onto
    -0.07
    POSITIVE LOGITS
    ä¼ĹæīĢåij¨çŁ¥
    0.10
    ä¸įåı¯æĢĿè®®
    0.09
    æĸ°åĬłåĿ¡
    0.09
    åĬłæĭ¿å¤§
    0.08
    缸è¾ħ缸æĪIJ
    0.08
    身临åħ¶å¢ĥ
    0.08
    enan
    0.07
    Ùĩ
    0.07
    æ¯Ľæ³½ä¸ľ
    0.07
    оÑĢо
    0.07
    Activations Density 0.001%

    No Known Activations