© 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. 58631
    Prev
    Next
    INDEX
    Explanations

    M-theory dimensions and form gauge

    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
    åľ¨çĶŁæ´»ä¸Ń
    -0.07
     plast
    -0.06
    åĿİ
    -0.06
    åĩºåħ·
    -0.06
    å²±
    -0.06
    witz
    -0.06
    ach
    -0.06
    Snap
    -0.06
    çĶŁæ´»ä¸Ń
    -0.06
    çıŃä¸Ĭ
    -0.06
    POSITIVE LOGITS
    ISTORY
    0.07
    adows
    0.07
    Äįina
    0.07
    indir
    0.07
    _CTX
    0.07
    Trail
    0.07
    .orig
    0.07
    STATIC
    0.07
     realms
    0.07
    olist
    0.07
    Activations Density 0.004%

    No Known Activations