© 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. 50280
    Prev
    Next
    INDEX
    Explanations

    version information and citations

    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
    å¹´æĪIJç«ĭ
    -0.08
    涤
    -0.08
    æ·¤
    -0.07
    äºĪ
    -0.07
    ÑģÑĤен
    -0.07
    elsey
    -0.07
    ä¸Ģä¸ĸ
    -0.07
    è¡Ĺ
    -0.07
    uze
    -0.07
    大è§Ĥ
    -0.07
    POSITIVE LOGITS
     nud
    0.07
    ç©¿åĩº
    0.07
    ullo
    0.06
     dol
    0.06
     mens
    0.06
    ÏĦÏģια
    0.06
    ulled
    0.06
    ovich
    0.06
    owan
    0.06
     conf
    0.06
    Activations Density 0.018%

    No Known Activations