© 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. 57645
    Prev
    Next
    INDEX
    Explanations

    biological markers and genes

    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
    è£ħ饰设计
    -0.07
    etem
    -0.07
     truc
    -0.07
    ière
    -0.06
    çŃīçļĦ
    -0.06
    åķ¼
    -0.06
    ovu
    -0.06
    ROWS
    -0.06
    odor
    -0.06
    elij
    -0.06
    POSITIVE LOGITS
    诸å¦Ĥ
    0.08
    -related
    0.08
    anca
    0.08
     goodies
    0.07
    amentais
    0.07
    æĤīæķ°
    0.07
    efs
    0.07
    listed
    0.07
    åĵªäºĽ
    0.07
     components
    0.07
    Activations Density 0.261%

    No Known Activations