© 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. 31440
    Prev
    Next
    INDEX
    Explanations

    functional abstracts

    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
    korb
    -0.07
    eger
    -0.07
    ors
    -0.07
    æĿ¥è¶Ĭ
    -0.07
    liness
    -0.06
    .opensource
    -0.06
    _unused
    -0.06
    è¡£æľįçļĦ
    -0.06
    ustr
    -0.06
    ilst
    -0.06
    POSITIVE LOGITS
    æħĭ
    0.08
    ÅĦczy
    0.08
    è´´æģ¯
    0.08
    dit
    0.08
    izan
    0.07
    æĢģ
    0.07
    Ñĸб
    0.07
    oose
    0.07
    zag
    0.07
    arah
    0.07
    Activations Density 0.001%

    No Known Activations