© 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. 48449
    Prev
    Next
    INDEX
    Explanations

    accommodation, ventilation, stocked, box, scroll, resolved, sequ, Intent

    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
    车æµģ
    -0.07
    caff
    -0.07
    راد
    -0.07
    rw
    -0.07
    emuk
    -0.07
    orate
    -0.06
    èĪŀæĽ²
    -0.06
    _POOL
    -0.06
    Wildcard
    -0.06
    Ùĩج
    -0.06
    POSITIVE LOGITS
    sic
    0.09
    itm
    0.07
    ave
    0.07
    anita
    0.07
    é©°åIJį
    0.06
    acia
    0.06
    æĹ¥æĻļéĹ´
    0.06
    èı²çī¹
    0.06
    è¡Įèĩ³
    0.06
     Jus
    0.06
    Activations Density 0.363%

    No Known Activations