© 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. 57497
    Prev
    Next
    INDEX
    Explanations

    describing differences or comparisons

    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
     yourselves
    -0.08
     Chambers
    -0.07
    [__
    -0.07
    ì¿
    -0.07
    	ext
    -0.07
    æľĢ大çļĦ
    -0.07
    æĺ¯æľĢ大çļĦ
    -0.07
    emel
    -0.07
    ynchronized
    -0.07
     EXT
    -0.07
    POSITIVE LOGITS
    对该
    0.09
    åıĪå¦Ĥ
    0.08
    è¿Ļ家
    0.07
    å°Ĩ该
    0.07
    ä»ħæѤ
    0.07
    为该
    0.07
    对äºİè¿Ļ个
    0.07
    ä¸įä»ħå¦ĤæѤ
    0.07
    该
    0.06
    ething
    0.06
    Activations Density 0.236%

    No Known Activations