© 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. 8692
    Prev
    Next
    INDEX
    Explanations

    numbers followed by periods or parentheses

    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
    pd
    -0.07
    Ãło
    -0.07
    满足äºĨ
    -0.07
    ¬
    -0.07
    åľ¨åįĬ
    -0.06
    åį«çĶŁç»Ħç»ĩ
    -0.06
    tanto
    -0.06
    immel
    -0.06
     Pfe
    -0.06
    ÑģкаÑĢ
    -0.06
    POSITIVE LOGITS
    åIJĮå·¥
    0.09
    оÑıÑĤ
    0.07
    idi
    0.07
    æħķåIJį
    0.07
    intang
    0.07
    ç·ł
    0.07
    æī«äºĮç»´çłģ
    0.07
    _PAR
    0.07
    ission
    0.07
    interop
    0.06
    Activations Density 0.015%

    No Known Activations