© 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. 23338
    Prev
    Next
    INDEX
    Explanations

    import statements

    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
     اÙĦÙħتر
    -0.07
    asha
    -0.07
     Schla
    -0.06
    _HEADERS
    -0.06
    éĤ£æł·
    -0.06
    emel
    -0.06
     autob
    -0.06
     mici
    -0.06
    VertexBuffer
    -0.06
    è¿ĺåı¯ä»¥åľ¨
    -0.06
    POSITIVE LOGITS
    ئ
    0.08
    _SOC
    0.07
    èĸ«
    0.07
    åĩĮ
    0.07
    irão
    0.07
    æŃ
    0.07
    ç®
    0.07
    ATUS
    0.06
    æ®ĺ
    0.06
    è¿Ļä¸ī
    0.06
    Activations Density 0.287%

    No Known Activations