© 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. 11327
    Prev
    Next
    INDEX
    Explanations

    Taylor expansion

    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
     Fresno
    -0.08
    æ¸ħ纯
    -0.07
     Legislat
    -0.07
    à°ĸ
    -0.07
     ex
    -0.07
    adera
    -0.06
    rious
    -0.06
    εÏį
    -0.06
    çļĦä¸ĢçĤ¹
    -0.06
    èĢĮéĢłæĪIJ
    -0.06
    POSITIVE LOGITS
    åĩij
    0.07
    æĽĻ
    0.07
    acus
    0.07
    éĢ¼è¿ij
    0.07
    ä¹Łå¥½
    0.07
     whip
    0.07
    teles
    0.07
     adap
    0.07
    nep
    0.07
    æĹĭ
    0.06
    Activations Density 0.001%

    No Known Activations