© 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. 15825
    Prev
    Next
    INDEX
    Explanations

    AI, Arduino, electricity, brain, nerve

    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¿ĻåŃ¦æľŁ
    -0.08
    ften
    -0.07
    anvas
    -0.07
    cte
    -0.07
    ilenames
    -0.07
     vigore
    -0.07
    icto
    -0.07
     ousted
    -0.07
    è¯ł
    -0.07
    ypes
    -0.07
    POSITIVE LOGITS
     arbitrarily
    0.10
     billions
    0.09
     massively
    0.08
    è¿Ļç§įä¸ľè¥¿
    0.08
    æŁIJç§į
    0.08
     conceivable
    0.08
    illions
    0.08
    çIJĨ论ä¸Ĭ
    0.07
     vastly
    0.07
     compress
    0.07
    Activations Density 0.043%

    No Known Activations