© 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. 31711
    Prev
    Next
    INDEX
    Explanations

    character sets

    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
    ê°Ħ
    -0.09
    insel
    -0.07
    å¿ĥçľ¼
    -0.07
    é½IJæĬĵ
    -0.07
    mai
    -0.07
    ==='
    -0.07
    fills
    -0.07
    लà¥įलà¥Ģ
    -0.07
    æ³ķæĺ¯
    -0.07
     lieferbar
    -0.07
    POSITIVE LOGITS
    lima
    0.07
    ifter
    0.06
    à¸į
    0.06
    ç´¯
    0.06
    aman
    0.06
    Mon
    0.06
     Operations
    0.06
    å¾ĹåĪĨ
    0.06
    eros
    0.06
    好ç¬ij
    0.06
    Activations Density 0.020%

    No Known Activations