© 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. 7545
    Prev
    Next
    INDEX
    Explanations

    parentheses and numbers

    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
    èµ·äºĨ
    -0.08
    ovu
    -0.07
    å¸Į
    -0.07
     alá
    -0.07
    ime
    -0.07
    ordes
    -0.07
    èĢĮè¿Ļç§į
    -0.06
    åºķæĿ¿
    -0.06
    .pm
    -0.06
    èĢĮè¿Ļ个
    -0.06
    POSITIVE LOGITS
    lÃł
    0.08
    <|box_end|>
    0.08
    areth
    0.08
    —including
    0.07
    elon
    0.07
    æħ°
    0.07
    γγελ
    0.07
    å·Ŀåİ¿
    0.07
    éĺ¿æĸ¯
    0.07
    —the
    0.07
    Activations Density 0.415%

    No Known Activations