© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42556
    Prev
    Next
    INDEX
    Explanations

    algebraic over $A$

    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
    etton
    -0.07
    ibat
    -0.07
    æİĪä¿¡
    -0.07
    pirit
    -0.07
    è°ĥ
    -0.06
    %@
    -0.06
    zion
    -0.06
    ç¡®ä¿Ŀå®īåħ¨
    -0.06
    åĭĻ
    -0.06
    splice
    -0.06
    POSITIVE LOGITS
    amo
    0.08
    uell
    0.08
    aday
    0.07
    americ
    0.07
    ustum
    0.07
    yaj
    0.07
    Broken
    0.07
    ucci
    0.07
    plete
    0.07
    agio
    0.07
    Activations Density 0.049%

    No Known Activations