© 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. 3495
    Prev
    Next
    INDEX
    Explanations

    warrant and notice

    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
     filetype
    -0.08
    ç´Ķ
    -0.07
    acad
    -0.07
    éĿĴæĿ¾
    -0.07
    è§Ĩ
    -0.07
    à¤ľà¥Ģ
    -0.07
    ÅĦcz
    -0.06
    askell
    -0.06
    æĹłå¿Į
    -0.06
     sight
    -0.06
    POSITIVE LOGITS
    åħ¬ç¤º
    0.08
    lese
    0.08
    fair
    0.07
    é¢ĦåijĬ
    0.07
    åħ¬å¹³çļĦ
    0.07
     Fair
    0.07
    Ñģен
    0.07
    æ¿
    0.07
     advance
    0.07
     familiar
    0.07
    Activations Density 0.032%

    No Known Activations