© 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. 15145
    Prev
    Next
    INDEX
    Explanations

    ãģ®ãģĭ or Japanese 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
    othe
    -0.09
    GBT
    -0.08
    lotte
    -0.08
    ocity
    -0.08
    licht
    -0.07
    loth
    -0.07
    acto
    -0.07
    stice
    -0.07
    Æ¡
    -0.07
    以赴
    -0.07
    POSITIVE LOGITS
     ìĭ¶
    0.10
     ìĭ¶ìĿĢ
    0.09
    èĩªå·±
    0.09
     ìĭ¶ìĸ´
    0.08
    ement
    0.08
    efois
    0.07
    ìļĶ
    0.07
    ï¼Į
    0.07
     mạc
    0.07
    åħ¶ä»ĸæĸ¹å¼ı
    0.06
    Activations Density 0.001%

    No Known Activations