© 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. 7766
    Prev
    Next
    INDEX
    Explanations

    return value

    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
    å¼ĢåıijæľīéĻIJåħ¬åı¸
    -0.07
     Marin
    -0.06
    Defaults
    -0.06
    éĻĢ
    -0.06
    .backends
    -0.06
    .solve
    -0.06
    人马
    -0.06
    å¼ĢèĢĥ
    -0.06
     base
    -0.06
    çªģ
    -0.06
    POSITIVE LOGITS
    <TResult
    0.08
    è¿ĩç¥ŀ
    0.08
    ounce
    0.08
    ارج
    0.07
    /results
    0.07
    /result
    0.07
    ussed
    0.07
    ascal
    0.07
    è¿ĶåĽŀåĢ¼
    0.07
    éĢģåĽŀ
    0.07
    Activations Density 0.055%

    No Known Activations