© 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. 64889
    Prev
    Next
    INDEX
    Explanations

    describing research and proposals

    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
     weird
    -0.12
     messed
    -0.12
     kinda
    -0.11
    -ish
    -0.11
     tricky
    -0.11
     punya
    -0.11
     vibe
    -0.11
     really
    -0.10
     messing
    -0.10
     pretty
    -0.10
    POSITIVE LOGITS
    亦åı¯
    0.11
    åĢĺèĭ¥
    0.11
    亦æľī
    0.11
     requisite
    0.11
     herein
    0.10
    æĬijæĪĸ
    0.10
    ä½ķç§į
    0.10
    å¦Ĥèĭ¥
    0.10
    æĽ´ä¸º
    0.10
    sequently
    0.09
    Activations Density 0.261%

    No Known Activations