© 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. 21038
    Prev
    Next
    INDEX
    Explanations

    computational modeling and study

    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
    semblies
    -0.10
    ighb
    -0.09
    landen
    -0.08
    occhi
    -0.08
    же
    -0.08
    utenant
    -0.08
    quit
    -0.08
    udet
    -0.08
    iger
    -0.08
    omis
    -0.08
    POSITIVE LOGITS
    -intensive
    0.09
    å¯ĨéĽĨåŀĭ
    0.08
    st
    0.07
     intensive
    0.07
    å¤§åĽ½
    0.06
    cern
    0.06
    mog
    0.06
    å¯ĨéĽĨ
    0.06
    ä»Ģä¹Īåij¢
    0.06
     computing
    0.06
    Activations Density 0.019%

    No Known Activations