© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26968
    Prev
    Next
    INDEX
    Explanations

    sentence start

    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
    edback
    -0.09
    .plist
    -0.08
    ç§ijæĬĢåĽŃ
    -0.08
    Ñģполни
    -0.08
    £¼
    -0.08
    å¾ħç»Ń
    -0.08
    ownik
    -0.08
    åIJ«ç³ĸ
    -0.08
    ัà¸ļ
    -0.08
     intele
    -0.08
    POSITIVE LOGITS
    æħİéĩį
    0.08
    write
    0.06
    ↵
    0.06
    /MM
    0.06
    ww
    0.06
    é»Ħæµ·
    0.05
    èĬ·
    0.05
    è¡Į
    0.05
     кли
    0.05
    使
    0.05
    Activations Density 0.001%

    No Known Activations