© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22927
    Prev
    Next
    INDEX
    Explanations

    sublicense rights

    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
    们çļĦ
    -0.07
    ä»¬åľ¨
    -0.07
    ãģ©ãĤĤ
    -0.07
     Gast
    -0.07
    ä¿©
    -0.07
    ListGroup
    -0.07
    aciones
    -0.07
    èłķ
    -0.07
     courrier
    -0.06
    .Col
    -0.06
    POSITIVE LOGITS
     Ãĩev
    0.07
    ç½ijæł¡
    0.07
    ฯ
    0.07
    onet
    0.07
    imson
    0.07
    éĬ·
    0.07
    utters
    0.07
    äºŃäºŃ
    0.07
    opin
    0.06
    á»ĥ
    0.06
    Activations Density 0.002%

    No Known Activations