© 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. 47137
    Prev
    Next
    INDEX
    Explanations

    barrier or roofing sheet

    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
    omen
    -0.07
    éĽķ
    -0.07
    æµĵæµĵ
    -0.07
    éĨī
    -0.06
     Bones
    -0.06
     Laden
    -0.06
    è¡Ģç³ĸ
    -0.06
    æ²īè¿·
    -0.06
     habitual
    -0.06
    è¡Ģ红
    -0.06
    POSITIVE LOGITS
    åį·æĿIJ
    0.11
     roofing
    0.10
    sheet
    0.10
    å±ĭéĿ¢
    0.09
    èĢIJåĢĻ
    0.09
     sheet
    0.08
    éĶļ
    0.08
    æİ¥ç¼Ŀ
    0.08
     moisture
    0.08
    éĵºè®¾
    0.08
    Activations Density 0.027%

    No Known Activations