© 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. 45335
    Prev
    Next
    INDEX
    Explanations

    comparative study or evaluation

    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
    ifiable
    -0.12
    ợt
    -0.08
    нÑı
    -0.08
    enticate
    -0.08
    gemar
    -0.08
    nya
    -0.08
    erkt
    -0.08
    ifying
    -0.07
    ////////////////////////////////////////////////////////////////////////////
    -0.07
    ת×Ļ
    -0.07
    POSITIVE LOGITS
    ity
    0.07
    æĹłåĩł
    0.07
    ¥
    0.07
    漩
    0.07
    <|box_end|>
    0.07
    è¾Ļ
    0.07
    /if
    0.06
    PRESS
    0.06
    ache
    0.06
    cede
    0.06
    Activations Density 0.005%

    No Known Activations