© 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. 22620
    Prev
    Next
    INDEX
    Explanations

    pdf distribution probabilities

    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
    cream
    -0.08
    æĦıæĢĿ
    -0.07
    çļĦä¸Ģèĩ´æĢ§
    -0.07
    è¡Į礼
    -0.07
    èĭįèĿĩ
    -0.07
    ä¸įä¸Ģèĩ´
    -0.06
    .average
    -0.06
    ä¸Ģèĩ´æĢ§
    -0.06
    ä¸Ģç¬Ķ
    -0.06
    çļĦæĦıæĢĿ
    -0.06
    POSITIVE LOGITS
     pdf
    0.08
     distribution
    0.08
     probabilities
    0.08
    åĪĨå¸ĥ
    0.08
    /pdf
    0.08
     distributions
    0.07
    -pdf
    0.07
     Prob
    0.07
    pdf
    0.07
    æ¦Ĥçİĩ
    0.07
    Activations Density 0.009%

    No Known Activations