© 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. 27340
    Prev
    Next
    INDEX
    Explanations

    leadership of

    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
    津津
    -0.07
    lems
    -0.07
    ìŀ¡
    -0.06
    æıIJé«ĺèĩªå·±çļĦ
    -0.06
    åħ·æľīéĩįè¦ģçļĦ
    -0.06
    _MACRO
    -0.06
    ä¸įè¾ľè´Ł
    -0.06
    .mk
    -0.06
    å®ŀå¤Ħ
    -0.06
    伤人
    -0.06
    POSITIVE LOGITS
    æĶ¯æĮģä¸ĭ
    0.12
    ä½ľçĶ¨ä¸ĭ
    0.12
    åĬłæĮģ
    0.12
    å¼ķ导ä¸ĭ
    0.11
    带é¢Ĩä¸ĭ
    0.10
    çļĦä½ľçĶ¨ä¸ĭ
    0.10
    çļĦæĶ¯æĮģä¸ĭ
    0.10
    æݨåĬ¨ä¸ĭ
    0.10
    åĬªåĬĽä¸ĭ
    0.10
    æĮĩ导ä¸ĭ
    0.10
    Activations Density 0.073%

    No Known Activations