© 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. 26692
    Prev
    Next
    INDEX
    Explanations

    ways to list things

    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
    acol
    -0.08
    æĹłå¾®ä¸įèĩ³
    -0.08
    ugat
    -0.08
    odio
    -0.08
    azel
    -0.07
    éĤ£äºĽäºº
    -0.07
    odos
    -0.07
    ä¸įçĶĺ
    -0.07
    anmar
    -0.07
    REDIS
    -0.07
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.09
    æĪĸå¤ļ个
    0.08
    åı¯ä»¥æĺ¯
    0.07
    çĶŁæ´»ä¸Ń
    0.07
    æĪĸ以ä¸Ĭ
    0.07
     hver
    0.07
    eyer
    0.07
    embe
    0.07
    èĩ³å°ij
    0.07
     Moody
    0.06
    Activations Density 0.054%

    No Known Activations