© 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. 19357
    Prev
    Next
    INDEX
    Explanations

    rounding or calculation

    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
    .dk
    -0.09
     Literal
    -0.08
    žÃŃ
    -0.08
    ench
    -0.08
    请ä¸ĭè½½
    -0.08
    ä¸ĭ载次æķ°
    -0.07
    ëĶ
    -0.07
    wart
    -0.07
    ackers
    -0.07
    /GPL
    -0.07
    POSITIVE LOGITS
    èĩ´
    0.08
    çķ¥
    0.07
    est
    0.07
    íĿ¥
    0.07
    etet
    0.07
     Spokane
    0.06
     slightly
    0.06
    еÑģÑĤ
    0.06
    ä¼°
    0.06
     légèrement
    0.06
    Activations Density 0.019%

    No Known Activations