© 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. 9269
    Prev
    Next
    INDEX
    Explanations

    license and GPLv2

    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
    atr
    -0.07
    bard
    -0.07
     Sing
    -0.07
     Dam
    -0.07
     mer
    -0.07
     ë³´ìĿ´
    -0.06
     rac
    -0.06
    大èĩ£
    -0.06
     Eig
    -0.06
    atty
    -0.06
    POSITIVE LOGITS
    lott
    0.08
    деÑĨ
    0.08
    gnos
    0.08
    aih
    0.07
    uré
    0.07
    <|quad_start|>
    0.07
    urb
    0.07
    urt
    0.07
    getDb
    0.07
    ebas
    0.07
    Activations Density 0.191%

    No Known Activations