© 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. 12148
    Prev
    Next
    INDEX
    Explanations

    LATIN, supplement, Exception, Scarff

    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
     traces
    -0.07
    udent
    -0.07
    orza
    -0.06
     trace
    -0.06
    第äºĮ段
    -0.06
    第äºĮæĿ¡
    -0.06
     tr
    -0.06
    agno
    -0.06
    åķ¡
    -0.06
    ream
    -0.06
    POSITIVE LOGITS
    omber
    0.08
     LATIN
    0.08
    Ĩµ
    0.08
    tus
    0.08
    ologii
    0.07
    lás
    0.07
    ibold
    0.07
    мÑĥÑĢ
    0.07
    andalone
    0.07
    èĻIJ
    0.07
    Activations Density 0.007%

    No Known Activations