© 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. 17600
    Prev
    Next
    INDEX
    Explanations

    research applications success

    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
    iaan
    -0.08
    ипе
    -0.07
    æĪIJåĬŁåľ°
    -0.07
    isNaN
    -0.07
    ofi
    -0.07
    operands
    -0.07
    OTS
    -0.07
    éģ
    -0.07
    itera
    -0.07
    æĪIJåĬŁçļĦ
    -0.07
    POSITIVE LOGITS
    åħ·æľīéĩįè¦ģ
    0.08
    ç»ĵç¼ĺ
    0.07
    raz
    0.07
    adm
    0.07
    ä¿¡èªī
    0.07
    ĽĦ
    0.07
    ear
    0.07
    æĦıä¹īéĩį大
    0.07
     importance
    0.06
    ä¹Łä¸º
    0.06
    Activations Density 0.428%

    No Known Activations