© 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. 57986
    Prev
    Next
    INDEX
    Explanations

    dates, times, and foreign titles

    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
    eland
    -0.08
    ayers
    -0.07
    vs
    -0.07
    auga
    -0.07
    _RET
    -0.07
    Vs
    -0.07
    è¾ŀ
    -0.07
    çļĦ大éĩı
    -0.06
    pps
    -0.06
    ROLS
    -0.06
    POSITIVE LOGITS
    ãģ¨ãĤĤ
    0.09
    åIJİèĢħ
    0.08
    ä¹Łè¡Į
    0.07
     equival
    0.07
    _IMPLEMENT
    0.07
     whichever
    0.07
    ucci
    0.07
     ëĸ¨ìĸ´ì§IJ
    0.06
    fam
    0.06
    бÑĢи
    0.06
    Activations Density 0.021%

    No Known Activations