© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48474
    Prev
    Next
    INDEX
    Explanations

    handbook, lp, and mathematics

    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
    eger
    -0.07
    Âł
    -0.07
    ï¼ĮãĢĬ
    -0.07
    âĢ
    -0.07
    âĢİ
    -0.07
    å®ŀå®ŀåľ¨
    -0.06
     fug
    -0.06
    «
    -0.06
    ãĢģ“
    -0.06
     pronto
    -0.06
    POSITIVE LOGITS
    +-+-
    0.08
    <tool_response>
    0.07
    orris
    0.07
    å®´
    0.07
    ãĤ¯ãĤ¿ãĥ¼
    0.07
    ascript
    0.07
    акÑĤеÑĢ
    0.07
    ÈĻti
    0.07
    entras
    0.07
     Fucking
    0.07
    Activations Density 0.867%

    No Known Activations