© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51897
    Prev
    Next
    INDEX
    Explanations

    end of line

    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
    usin
    -0.07
    è¯»æľ¬
    -0.07
    对å®ĥ
    -0.07
    اÙĨÙĪ
    -0.07
    \":\"
    -0.07
    ammed
    -0.07
    .reload
    -0.06
    ú
    -0.06
    ä»İæĪijåģļèµ·
    -0.06
    æĥ³å°½
    -0.06
    POSITIVE LOGITS
    Ùĭ
    0.07
    ï¼Ľ
    0.07
    pees
    0.06
    .factory
    0.06
    дÑijÑĤ
    0.06
    -rated
    0.06
    大è¯Ŀ
    0.06
    гон
    0.06
    ï¸ı
    0.05
    Âł
    0.05
    Activations Density 0.316%

    No Known Activations