© 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. 58261
    Prev
    Next
    INDEX
    Explanations

    unsigned integer or comment markers

    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
    å¨ĥå¨ĥ
    -0.07
    ç»ĻåĪ«äºº
    -0.07
    ä¸İéĿŀ
    -0.06
    icz
    -0.06
    ic
    -0.06
     شأÙĨ
    -0.06
    apl
    -0.06
     ac
    -0.06
    cec
    -0.06
     perp
    -0.06
    POSITIVE LOGITS
    ç´§æİ¥çĿĢ
    0.08
    á»ĵng
    0.07
    ä¸Ģè¡Į
    0.07
    ingham
    0.07
    pong
    0.07
    á»ĥ
    0.06
    èĥ½å¹²
    0.06
     dĩ
    0.06
    enton
    0.06
     proceeded
    0.06
    Activations Density 0.009%

    No Known Activations