© 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. 41073
    Prev
    Next
    INDEX
    Explanations

    questions about topics

    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
    è¿ĽéĢĢ
    -0.08
    è¿Ľè¡Įæµĭè¯ķ
    -0.08
    acc
    -0.07
    øv
    -0.07
    ypi
    -0.07
    认åĩĨ
    -0.07
    æį®æѤæĵįä½ľ
    -0.07
     Toll
    -0.07
    år
    -0.07
     matemat
    -0.07
    POSITIVE LOGITS
     comprehensive
    0.10
    çļĦåħ¨éĿ¢
    0.08
    åħ¨éĿ¢çļĦ
    0.08
    åħ¨éĿ¢
    0.08
    rena
    0.07
    没æľīæŶéĹ´
    0.07
     Comprehensive
    0.07
     esplic
    0.07
     обÑĪи
    0.07
    _EXP
    0.07
    Activations Density 0.039%

    No Known Activations