© 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. 21300
    Prev
    Next
    INDEX
    Explanations

    background section, music, color, noise, image

    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
    надÑĨ
    -0.10
    kenal
    -0.09
    ковод
    -0.09
    ifiable
    -0.09
    надÑĨаÑĤи
    -0.09
    надÑĨаÑĤÑĮ
    -0.09
    erator
    -0.09
    bacher
    -0.09
    gemeinschaft
    -0.09
    ÑĶÑĹ
    -0.09
    POSITIVE LOGITS
    ed
    0.11
    ness
    0.10
     tảng
    0.08
     belakang
    0.08
    s
    0.08
    ↵
    0.08
    sWith
    0.07
    less
    0.07
    les
    0.07
    edly
    0.07
    Activations Density 0.034%

    No Known Activations