© 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. 57878
    Prev
    Next
    INDEX
    Explanations

    advance/advantage

    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
    avanaugh
    -0.09
    веÑĤ
    -0.09
    deÅŁ
    -0.08
    idou
    -0.08
    aring
    -0.07
    atoes
    -0.07
     darn
    -0.07
    глÑĥ
    -0.07
    ÑģлÑĸ
    -0.07
    ÑģмоÑĤÑĢиÑĤе
    -0.07
    POSITIVE LOGITS
    antage
    0.09
    enticate
    0.08
    apta
    0.08
    áĥĿáĥij
    0.08
    ä¸įæĺİçļĦ
    0.08
    گاÙĩ
    0.08
    tır
    0.08
    ement
    0.08
    colar
    0.08
    人士
    0.07
    Activations Density 0.063%

    No Known Activations