© 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. 63981
    Prev
    Next
    INDEX
    Explanations

    numbers followed by years or divisions

    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
    arsed
    -0.08
    èĢĮçŁ¥
    -0.07
    ç¡®å®ļ
    -0.07
    大çļĦ
    -0.06
    为主
    -0.06
    ارÙģ
    -0.06
    ä¸įåİĮ
    -0.06
    lim
    -0.06
    åī¯åĮºéķ¿
    -0.06
     themselves
    -0.06
    POSITIVE LOGITS
    ’B
    0.08
    issan
    0.08
    etet
    0.08
    udah
    0.08
    Unnamed
    0.08
    ocard
    0.07
    缸åħ³æݨèįIJ
    0.07
    ezet
    0.07
    ServletRequest
    0.07
    atcher
    0.07
    Activations Density 0.001%

    No Known Activations