© 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. 50408
    Prev
    Next
    INDEX
    Explanations

    DONE

    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
    ipay
    -0.08
    araan
    -0.08
    ¬ģ
    -0.08
    orsk
    -0.08
    ocate
    -0.07
    ĥĿ
    -0.07
    achel
    -0.07
    erk
    -0.07
    è¾Ļ
    -0.07
    ë°į
    -0.07
    POSITIVE LOGITS
    rist
    0.07
    fatt
    0.06
    ä½Ĩä¸įéĻIJäºİ
    0.06
    anam
    0.06
     Col
    0.06
    :
    0.06
    isine
    0.06
    flat
    0.06
    ä¹İ
    0.06
    精讲
    0.06
    Activations Density 0.001%

    No Known Activations