© 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. 39312
    Prev
    Next
    INDEX
    Explanations

    epistemology, knowledge, seeker

    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
    è¹Ī
    -0.08
    erÃŃa
    -0.08
    isplay
    -0.07
    fass
    -0.07
    ized
    -0.07
    izada
    -0.07
     nomine
    -0.07
    enames
    -0.07
    ENCHMARK
    -0.07
    izado
    -0.07
    POSITIVE LOGITS
    æ±Ĥ羣
    0.09
    åĴĮå®ŀè·µ
    0.09
    (ep
    0.08
    éĢĶå¾Ħ
    0.07
    ä¸İå®ŀè·µ
    0.07
     ep
    0.07
    羣çIJĨ
    0.07
    agog
    0.07
    ep
    0.07
    åĴĮè¡Į为
    0.07
    Activations Density 0.003%

    No Known Activations