© 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. 11517
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    º
    -0.09
    <|box_end|>
    -0.09
    hift
    -0.09
    centage
    -0.09
    ettings
    -0.08
    pace
    -0.08
    ளà¯į
    -0.08
    hetto
    -0.08
    naments
    -0.08
    ////////////////////////////////////////////////////
    -0.08
    POSITIVE LOGITS
    icky
    0.07
    enni
    0.07
    irl
    0.06
    иÑĤелÑĮно
    0.06
    ermen
    0.06
    ively
    0.06
    oker
    0.06
    گرÛĮ
    0.06
    rss
    0.06
    entic
    0.06
    Activations Density 0.284%

    No Known Activations