© 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. 25034
    Prev
    Next
    INDEX
    Explanations

    code block punctuation

    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
    ä¸ĢåĽŀ
    -0.07
    .listeners
    -0.06
    éķ¿æľŁçļĦ
    -0.06
     Zus
    -0.06
    unde
    -0.06
    aporte
    -0.06
    atto
    -0.06
     halfway
    -0.06
    OrCreate
    -0.06
    arci
    -0.06
    POSITIVE LOGITS
    until
    0.09
    _until
    0.08
    UAR
    0.08
    褥
    0.08
    缴èĩ³
    0.08
    é£Ľãģ°
    0.08
    macher
    0.07
    ابع
    0.07
    CUR
    0.07
     tÃł
    0.07
    Activations Density 0.009%

    No Known Activations