© 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. 61574
    Prev
    Next
    INDEX
    Explanations

    triple-negative, amino-terminal derivatives, replacements, hemoglobin, A-II

    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
    ahan
    -0.07
    inel
    -0.07
    urch
    -0.06
    uran
    -0.06
    .figure
    -0.06
     Tre
    -0.06
     %.
    -0.06
     Deprecated
    -0.06
    ä¸įèĥ½è¶ħè¿ĩ
    -0.06
    央
    -0.06
    POSITIVE LOGITS
    XB
    0.09
    ucie
    0.08
    £¼
    0.08
    串çļĦ
    0.08
    anded
    0.08
    anford
    0.08
    åħ¨è·¯æ®µ
    0.08
    ivered
    0.08
    _suite
    0.08
    oling
    0.08
    Activations Density 0.001%

    No Known Activations