© 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. 64863
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and structures

    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
    æ»ĭ
    -0.07
    Ral
    -0.07
     unt
    -0.06
    .cms
    -0.06
    åĬ±
    -0.06
    isca
    -0.06
    J
    -0.06
    Aware
    -0.06
    çŁ¥
    -0.06
    ä¸Ģç§į
    -0.06
    POSITIVE LOGITS
     waarin
    0.10
    åħĭéļ¾
    0.09
    ä½łä¸ºä»Ģä¹Ī
    0.09
    inster
    0.08
    ä½łä¸Ģå®ļ
    0.08
    éĩĩçĶ¨çļĦæĺ¯
    0.08
    ä¸ŃçļĦåºĶçĶ¨
    0.08
    eita
    0.08
    arkin
    0.08
    ä¸Ńäºļ
    0.08
    Activations Density 0.018%

    No Known Activations