© 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. 41132
    Prev
    Next
    INDEX
    Explanations

    job fair deliverables

    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
    ÑĨин
    -0.08
    íĭ´
    -0.08
    èĭ·
    -0.07
    ripsi
    -0.07
    ä¸įå®Įåħ¨ç»Łè®¡
    -0.07
    urada
    -0.07
    riba
    -0.07
    ELY
    -0.07
    æħ¢è¡Į
    -0.07
    obuf
    -0.07
    POSITIVE LOGITS
    enville
    0.07
     شأÙĨ
    0.07
    avian
    0.06
    furt
    0.06
     av
    0.06
    交åĩº
    0.06
    chn
    0.06
    Contrib
    0.06
    åºľ
    0.06
    ä¸įæį¢
    0.06
    Activations Density 0.835%

    No Known Activations