© 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. 25636
    Prev
    Next
    INDEX
    Explanations

    ordering instructions

    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
    ä¸İ建议
    -0.09
    å°ıè®°èĢħ
    -0.08
    ÑĦеÑĢ
    -0.08
    æĹłæģĻ
    -0.08
    æĹ¥ä¸º
    -0.08
    -scripts
    -0.08
    åĪĨåĪ«ä¸İ
    -0.08
    tot
    -0.07
    èĢ¿èĢ¿
    -0.07
    è´µåľ¨
    -0.07
    POSITIVE LOGITS
    èĴ²
    0.06
     orient
    0.06
    æľĢ常çĶ¨çļĦ
    0.06
    using
    0.06
    .Comparator
    0.06
     using
    0.06
    ach
    0.06
    اÙĩ
    0.06
    ä¸Ģ缴éĥ½æĺ¯
    0.06
     employing
    0.06
    Activations Density 0.006%

    No Known Activations