© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44679
    Prev
    Next
    INDEX
    Explanations

    "arity", "ejo", "othe" followed by words like "San", "Bloomberg", "Ramp"

    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
    Negative Logits
    èĩªå·±
    -0.10
    zeitig
    -0.09
    —or
    -0.09
    -ish
    -0.08
    amma
    -0.07
    æľ¬ç«ĻæīĢæľī
    -0.07
    —not
    -0.07
    —that
    -0.07
    doÄŁan
    -0.07
    èĩªå·±æ²¡æľī
    -0.07
    POSITIVE LOGITS
    arity
    0.10
    ejo
    0.09
    othe
    0.09
    俱ä¹IJéĥ¨
    0.08
    覧
    0.08
    ر
    0.08
    缸è¾ħ缸æĪIJ
    0.08
    echs
    0.08
    o
    0.08
    äºĭåįĬåĬŁåĢį
    0.08
    Activations Density 0.119%

    No Known Activations