© 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. 15046
    Prev
    Next
    INDEX
    Explanations

    XML or HTML markup with attributes

    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
    ä¸Ģä¸ĭ
    -0.08
    inx
    -0.07
    оÑī
    -0.07
    to
    -0.07
    t
    -0.07
    สำà¸Ħัà¸įà¸Ĥà¸Ńà¸ĩ
    -0.07
    tr
    -0.07
    of
    -0.06
    omb
    -0.06
    so
    -0.06
    POSITIVE LOGITS
    ़
    0.14
    ł
    0.10
    AGEM
    0.10
    usada
    0.09
    rame
    0.09
    enen
    0.09
    ÏĥÏį
    0.09
    enheim
    0.09
    çŁ¥çļĦ
    0.09
    ATAB
    0.09
    Activations Density 0.153%

    No Known Activations