© 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. 10380
    Prev
    Next
    INDEX
    Explanations

    maximum or limit

    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
    ancel
    -0.09
    CTOR
    -0.07
    cik
    -0.07
    å·¥åѦéĻ¢
    -0.07
    ĭ
    -0.07
    anou
    -0.07
    εÏĤ
    -0.07
    etic
    -0.07
    sg
    -0.07
     بطاÙĤØ©
    -0.07
    POSITIVE LOGITS
    hoff
    0.07
    å¾·æĭī
    0.06
    égor
    0.06
    éĻIJ
    0.06
     Warp
    0.06
    驻车
    0.06
    å§Ĩæĸ¯
    0.06
     Enter
    0.06
    inn
    0.06
     hundreds
    0.06
    Activations Density 0.002%

    No Known Activations