© 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. 22294
    Prev
    Next
    INDEX
    Explanations

    to the point where

    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
    ież
    -0.09
    eldon
    -0.09
    atil
    -0.08
    azier
    -0.08
    ptime
    -0.08
     dalje
    -0.08
    endela
    -0.08
     λοι
    -0.08
    iming
    -0.08
    åIJĮä¸Ĭ
    -0.08
    POSITIVE LOGITS
    çļĦåľ°æŃ¥
    0.11
    以èĩ³äºİ
    0.09
    足以
    0.09
    称å¾Ĺä¸Ĭ
    0.08
     aż
    0.08
    åı¯ä»¥è¯´æĺ¯
    0.07
    æĪIJ为ä¸Ģç§į
    0.07
     warrant
    0.07
    åı¯ä»¥è¯´
    0.07
    åľ°æŃ¥
    0.07
    Activations Density 0.236%

    No Known Activations