© 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. 7692
    Prev
    Next
    INDEX
    Explanations

    specific details or types

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.06
    é¦ĸ
    -0.06
    èŁ
    -0.06
     Hood
    -0.05
    äºĮä¸Ń
    -0.05
     individually
    -0.05
    ohana
    -0.05
    èį·
    -0.05
    asion
    -0.05
     explicitly
    -0.05
    POSITIVE LOGITS
    sic
    0.09
    culares
    0.08
    geist
    0.08
    åĴĮä¿¡æģ¯åĮĸ
    0.08
    SETS
    0.08
    åĩłæĿ¡
    0.08
    oule
    0.08
    cular
    0.08
    ogar
    0.08
    akov
    0.07
    Activations Density 0.415%

    No Known Activations