© 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. 40660
    Prev
    Next
    INDEX
    Explanations

    multiplication or by expressions

    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
    erty
    -0.08
    ASSES
    -0.08
    zat
    -0.07
    asca
    -0.07
    utton
    -0.07
    æĹłæŃ¢
    -0.07
    èĢĮèĩªå·±
    -0.06
    би
    -0.06
    çŁ¥éģĵä½ł
    -0.06
    estig
    -0.06
    POSITIVE LOGITS
    /OR
    0.09
    éĢĤå½ĵçļĦ
    0.09
    ัà¹īà¸ĩ
    0.08
     optionally
    0.07
    åIJĦèĩªçļĦ
    0.07
    éĢĤå½ĵ
    0.07
    raquo
    0.07
     lir
    0.07
     whatever
    0.07
     appropriately
    0.07
    Activations Density 0.002%

    No Known Activations