© 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. 23900
    Prev
    Next
    INDEX
    Explanations

    vector usage with types

    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
    eningen
    -0.09
    enticated
    -0.08
    ELLI
    -0.08
    åłĤåłĤ
    -0.07
    igu
    -0.07
    гаÑĢ
    -0.07
    kena
    -0.07
     fou
    -0.07
    istrator
    -0.07
    è¸ıè¸ıå®ŀ
    -0.06
    POSITIVE LOGITS
    çļĦäººä¹Ł
    0.08
    ówczas
    0.07
    zinho
    0.07
    лав
    0.07
    Maker
    0.07
    lare
    0.07
    ':[
    0.07
    *>(
    0.07
    {}]
    0.06
    ':['
    0.06
    Activations Density 0.025%

    No Known Activations