© 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. 40745
    Prev
    Next
    INDEX
    Explanations

    special characters

    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
    ×Ļת
    -0.08
    ilier
    -0.07
    ool
    -0.07
    çļĦå¿ĥ声
    -0.07
    quoi
    -0.07
     dirname
    -0.06
    ÑģÑı
    -0.06
    为èį£
    -0.06
    ournal
    -0.06
    ãĤĪãģĨãģª
    -0.06
    POSITIVE LOGITS
    æĪIJèį¯
    0.07
    tay
    0.07
    axes
    0.07
    åħ°å¾·
    0.07
    ì°¨ë¡Ģ
    0.07
    vine
    0.07
    onto
    0.07
    apor
    0.07
    ħ
    0.06
    ones
    0.06
    Activations Density 0.023%

    No Known Activations