© 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. 19887
    Prev
    Next
    INDEX
    Explanations

    emission characteristics

    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
    ../../../
    -0.11
    kker
    -0.09
    åħ®åħ®
    -0.08
    umbs
    -0.08
    ŀ
    -0.08
    à¸ĸà¹īวà¸Ļ
    -0.07
    åij³åĦ¿
    -0.07
     hinweg
    -0.07
    ../../
    -0.07
    ifications
    -0.07
    POSITIVE LOGITS
    erald
    0.09
    ively
    0.09
    æĸ°èĤ¡
    0.08
    igrant
    0.08
    igration
    0.08
    ERAL
    0.08
    /download
    0.07
    ä¸įåĩºåİ»
    0.07
    ÑĥÑīеÑģÑĤв
    0.07
    unno
    0.07
    Activations Density 0.079%

    No Known Activations