© 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. 3268
    Prev
    Next
    INDEX
    Explanations

    chemical compounds

    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
    æķĻèĤ²èĢĥè¯ķ
    -0.07
     conditioning
    -0.07
    æĬĬåŃ¦ä¹ł
    -0.07
     conditioned
    -0.07
    åIJij被åijĬ
    -0.07
    rale
    -0.07
    ilon
    -0.07
    ç¼Ŀ
    -0.07
     Conditioning
    -0.07
    ä
    -0.07
    POSITIVE LOGITS
    åĮĸåIJĪ
    0.11
     atomic
    0.09
    åİŁåŃIJ
    0.08
     Atomic
    0.08
    æľ¬é¢Ĩ
    0.08
    atomic
    0.07
    çļĦåIJį称
    0.07
    èĩªçĦ¶çķĮ
    0.07
    æ°§
    0.07
    æĢ»ä»·
    0.07
    Activations Density 0.001%

    No Known Activations