© 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. 49963
    Prev
    Next
    INDEX
    Explanations

    structure and governance

    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
    erate
    -0.09
    ATAB
    -0.09
    atego
    -0.08
    stur
    -0.08
    èĻ
    -0.08
    ç¬Ķ
    -0.08
    readystatechange
    -0.08
    lsi
    -0.08
    è´
    -0.08
    utine
    -0.08
    POSITIVE LOGITS
    ä¸įåĩº
    0.07
    æĬĬ人
    0.06
    och
    0.06
    ako
    0.06
    L
    0.06
    inker
    0.06
     h
    0.05
    u
    0.05
     lan
    0.05
     l
    0.05
    Activations Density 0.049%

    No Known Activations