© 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. 41092
    Prev
    Next
    INDEX
    Explanations

    viable option or alternative

    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
    éļıå¿ĥ
    -0.07
    ongyang
    -0.07
    ä¸ĩæĪ·
    -0.07
    纲
    -0.07
    icach
    -0.07
    ä¸Ńå¿ĥåĮ»éĻ¢
    -0.07
    éĴ¥
    -0.07
    licht
    -0.07
    Æ¡m
    -0.07
    .Parse
    -0.07
    POSITIVE LOGITS
    pst
    0.07
    deb
    0.07
    iel
    0.07
    Ö·
    0.07
    èĢį
    0.07
    ä¸Ĭå²Ĺ
    0.07
    деÑĢ
    0.06
    elor
    0.06
    ελ
    0.06
    ç¥ī
    0.06
    Activations Density 0.001%

    No Known Activations