© 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. 49137
    Prev
    Next
    INDEX
    Explanations

    independent words and suffixes

    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
    å¦Ĥä½ķåģļ好
    -0.08
    OLA
    -0.08
    IZER
    -0.08
    amar
    -0.08
    izer
    -0.08
    actory
    -0.08
    TERS
    -0.08
    tritt
    -0.07
    acent
    -0.07
    å¿ĥèĥ¸
    -0.07
    POSITIVE LOGITS
    èµ·æĿ¥
    0.07
    essione
    0.07
    åľ¨ä¸Ģèµ·
    0.07
    宣è¨Ģ
    0.07
    ç»ĦæĪIJçļĦ
    0.07
    ед
    0.07
     pairwise
    0.06
    éĽı
    0.06
    å½¼æѤ
    0.06
    èĸĦèį·
    0.06
    Activations Density 0.001%

    No Known Activations