© 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. 42066
    Prev
    Next
    INDEX
    Explanations

    date range and bounds

    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
    tempt
    -0.08
    UGHT
    -0.08
    ensa
    -0.07
    коÑĢи
    -0.07
    emt
    -0.07
    noch
    -0.07
    å¥ĩå¦ĻçļĦ
    -0.07
     BOOT
    -0.07
    (dot
    -0.06
    åİŁå§ĭçļĦ
    -0.06
    POSITIVE LOGITS
    ä¸ĭéĻIJ
    0.10
     min
    0.10
    .min
    0.09
    æľĢå°ı
    0.08
    åĴĮæľĢ
    0.08
    ,min
    0.08
    min
    0.08
     мин
    0.08
     bounds
    0.08
    /min
    0.08
    Activations Density 0.034%

    No Known Activations