© 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. 1333
    Prev
    Next
    INDEX
    Explanations

    styryl and derivatives

    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
     surface
    -0.06
    -
    -0.06
     br
    -0.06
    alse
    -0.06
    æ°ij
    -0.06
    ibel
    -0.06
    é»ĺå¥ij
    -0.06
    .memo
    -0.05
    éĿ¢
    -0.05
     Bowman
    -0.05
    POSITIVE LOGITS
    alink
    0.10
     gesta
    0.09
     attached
    0.09
    åıĶ
    0.09
    éĩij森
    0.09
    trop
    0.08
    æĪĸ缴æİ¥
    0.08
    astia
    0.08
    ç»´æĸ¯
    0.08
    esa
    0.08
    Activations Density 0.040%

    No Known Activations