© 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. 24859
    Prev
    Next
    INDEX
    Explanations

    assembly lines

    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
    ymar
    -0.09
    ìĬ¤ëŁ½
    -0.09
    zsche
    -0.09
    nows
    -0.08
    ़
    -0.08
    uong
    -0.08
    俱ä¹IJéĥ¨
    -0.08
    amenta
    -0.08
    ızı
    -0.08
    åĻĮ
    -0.08
    POSITIVE LOGITS
    ments
    0.10
    sembled
    0.08
    ment
    0.08
    -sama
    0.08
     Ùħجدد
    0.08
    mates
    0.07
    ä¼Ļ
    0.07
    semble
    0.07
    sembles
    0.07
    æĭ¢
    0.07
    Activations Density 0.050%

    No Known Activations