© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56771
    Prev
    Next
    INDEX
    Explanations

    legal citations and abbreviations

    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
    vik
    -0.08
    ihen
    -0.07
    à§ģà¦ķ
    -0.07
    ifes
    -0.07
    varo
    -0.07
    çĻ½æĹ¥
    -0.07
    éĺģä¸ĭ
    -0.07
    uck
    -0.07
    ved
    -0.07
    itori
    -0.07
    POSITIVE LOGITS
    ä¸į容
    0.07
    ç»ı纪åħ¬åı¸
    0.07
    å®ķ
    0.07
    zew
    0.06
    ebak
    0.06
    ç«ł
    0.06
    ØŃÙĪÙĦ
    0.06
    交ä¼ļ
    0.06
    æĭĽ
    0.06
    ående
    0.06
    Activations Density 0.074%

    No Known Activations