© 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. 20976
    Prev
    Next
    INDEX
    Explanations

    results are presented

    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
    è§Ħå®ļçļĦåħ¶ä»ĸ
    -0.09
     cooper
    -0.08
    ArrayType
    -0.08
    iertel
    -0.08
    STYPE
    -0.08
    å±ķå¼Ģåħ¨æĸĩ
    -0.08
    emento
    -0.08
    лиÑĩно
    -0.08
     klima
    -0.08
    olan
    -0.08
    POSITIVE LOGITS
    æŃ£ç¡®çļĦæĺ¯
    0.10
    éĶĻ误çļĦæĺ¯
    0.09
    ä¸įæŃ£ç¡®çļĦæĺ¯
    0.09
    çļĦ说æ³ķ
    0.07
    亨
    0.07
     Avery
    0.07
    æľī误
    0.07
    æĬľ
    0.06
    ä¸ĭåĪĹ说æ³ķ
    0.06
    èıģ
    0.06
    Activations Density 0.004%

    No Known Activations