© 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. 33269
    Prev
    Next
    INDEX
    Explanations

    based on

    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
    вÑĸÑĢ
    -0.09
    èĢģæľīæīĢ
    -0.08
    åħ¶ä»ĸåªĴä½ĵ
    -0.08
    ç¼ĺçĶ±
    -0.08
    urge
    -0.08
    sä
    -0.08
    Ñģин
    -0.08
    னி
    -0.07
    nitz
    -0.07
    è¿Ŀæ³ķåĴĮä¸įèī¯ä¿¡æģ¯ä¸¾æĬ¥
    -0.07
    POSITIVE LOGITS
     recent
    0.09
     observations
    0.09
    ç»ıéªĮåĴĮ
    0.08
    å®ŀéĻħæĥħåĨµ
    0.08
     facts
    0.08
     prevailing
    0.08
    å·²æľī
    0.08
     experience
    0.08
    ç»ıéªĮ
    0.08
     expert
    0.08
    Activations Density 0.043%

    No Known Activations