© 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. 23241
    Prev
    Next
    INDEX
    Explanations

    stated, name, summary, prepared, get

    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
    çľĭçľĭåIJ§
    -0.08
     urgently
    -0.08
    太éĩį
    -0.08
    adt
    -0.08
    jeta
    -0.08
    ercial
    -0.07
    adet
    -0.07
    讲讲
    -0.07
     salva
    -0.07
    кÑĥл
    -0.07
    POSITIVE LOGITS
    并æıIJåĩº
    0.07
    æıIJåĩºäºĨ
    0.07
    ä»ĸçŁ¥éģĵ
    0.07
    ä¸įæĥľ
    0.07
    ä¸į误
    0.07
     correct
    0.07
    åŃ¦ä»¥èĩ´çĶ¨
    0.06
    çĻ¾å¿Ļ
    0.06
     knows
    0.06
     conocen
    0.06
    Activations Density 0.024%

    No Known Activations