© 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. 17550
    Prev
    Next
    INDEX
    Explanations

    equations and calculations

    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
    æĥ³çļĦ
    -0.08
    æīĵçļĦ
    -0.07
    åħ¨éĿ¢
    -0.07
     buflen
    -0.07
    بت
    -0.06
    ä¸Ģ缴
    -0.06
    çĴ§
    -0.06
    veen
    -0.06
    æī¿æı½
    -0.06
    åĴĮä¸į
    -0.06
    POSITIVE LOGITS
     semiclassical
    0.09
    æĬĬåŃ¦ä¹ł
    0.08
     propag
    0.08
    å°±åı¯ä»¥åľ¨
    0.07
     inciden
    0.07
    azel
    0.07
    matrix
    0.07
    åĪĻåľ¨
    0.07
    imenta
    0.07
     MATRIX
    0.07
    Activations Density 0.036%

    No Known Activations