© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9136
    Prev
    Next
    INDEX
    Explanations

    Orbit Chart, Hammer.js

    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
    jern
    -0.07
    æ·¡
    -0.06
    apl
    -0.06
     lec
    -0.06
    æİ¥éĢļ
    -0.06
    اÙħÙĬÙĨ
    -0.06
    sth
    -0.06
    aec
    -0.06
    ãĢħ
    -0.06
    ier
    -0.06
    POSITIVE LOGITS
    velt
    0.09
     perpetr
    0.09
    inschaft
    0.09
    endam
    0.08
    roda
    0.08
    zeÅĽ
    0.08
     orb
    0.08
    ä¸Ńæļij
    0.07
     orbits
    0.07
    _MSK
    0.07
    Activations Density 0.010%

    No Known Activations