© 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. 43754
    Prev
    Next
    INDEX
    Explanations

    place .right, ball on .NotNull the, practice of, job Linux

    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
    zinho
    -0.09
    꽤
    -0.08
    <|box_end|>
    -0.08
    oram
    -0.08
    COPE
    -0.08
    ities
    -0.08
    rhein
    -0.08
    TokenType
    -0.08
    velt
    -0.08
    çon
    -0.08
    POSITIVE LOGITS
    ä¸įåĪ°ä½į
    0.09
    èIJ½å®ŀ
    0.08
    è¡Ķæİ¥
    0.07
    ç»ĨèĬĤ
    0.07
    ef
    0.07
    å®ŀå¤Ħ
    0.07
    ../../
    0.07
    à¸Ľà¸¥à¸µà¸ģ
    0.07
    好èĩªå·±çļĦ
    0.07
    æĬĵ好
    0.07
    Activations Density 0.002%

    No Known Activations