© 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. 17666
    Prev
    Next
    INDEX
    Explanations

    turn on or off

    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
     halnya
    -0.09
    ़
    -0.08
    ়
    -0.08
    ural
    -0.08
     dÃłng
    -0.08
    orus
    -0.08
    erenc
    -0.08
     vét
    -0.07
    oret
    -0.07
    jenigen
    -0.07
    POSITIVE LOGITS
    äch
    0.11
    stile
    0.10
    abouts
    0.09
    åį³éĢĿ
    0.09
    åijIJ
    0.08
    about
    0.07
    ä¸įè¿ĩæĿ¥
    0.07
    pike
    0.07
    ings
    0.07
    piler
    0.07
    Activations Density 0.034%

    No Known Activations