© 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. 19254
    Prev
    Next
    INDEX
    Explanations

    file download links and expired

    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
    itness
    -0.08
    èĬ³èįī
    -0.08
    æľī以ä¸ĭ
    -0.07
    ighed
    -0.07
     \`
    -0.07
    ifikasi
    -0.06
    ãĥŁãĤ¢
    -0.06
    çal
    -0.06
    _tools
    -0.06
    æľīçļĦåIJĮåѦ
    -0.06
    POSITIVE LOGITS
    åģı
    0.08
    _procs
    0.08
    adoo
    0.08
    微信æī«ä¸Ģæī«
    0.07
    xl
    0.07
    æĭ¿
    0.07
     prominence
    0.07
    icas
    0.07
    èĢIJå¿ĥåľ°
    0.06
    udes
    0.06
    Activations Density 0.305%

    No Known Activations