© 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. 42341
    Prev
    Next
    INDEX
    Explanations

    code separators and identifiers

    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
    人åħ³æ³¨
    -0.07
    lipp
    -0.07
    nali
    -0.07
    人åĸľæ¬¢
    -0.06
    annes
    -0.06
    enia
    -0.06
    eres
    -0.06
    ĥ
    -0.06
    è·Łè¿Ľ
    -0.06
    greg
    -0.06
    POSITIVE LOGITS
    峪
    0.09
    ibbon
    0.08
    èŁĢ
    0.08
    amp
    0.08
    ifice
    0.07
    /or
    0.07
    çĽ¸æľĽ
    0.07
    ä¸įæķ£
    0.07
    æĹ¥åIJİçļĦ
    0.07
    åħ·å¤ĩä¸Ģå®ļçļĦ
    0.07
    Activations Density 0.023%

    No Known Activations