© 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. 26030
    Prev
    Next
    INDEX
    Explanations

    of particular interest

    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
    авли
    -0.08
    ÑħождениÑı
    -0.07
    jero
    -0.07
    aneously
    -0.07
    ìľ¨ìĿĦ
    -0.07
    ons
    -0.07
    funk
    -0.07
    ¯
    -0.07
    祸é¦ĸ
    -0.07
     nutshell
    -0.07
    POSITIVE LOGITS
    ftime
    0.09
    entimes
    0.09
    ä¸įèĩª
    0.08
    alcon
    0.07
    amin
    0.07
    ãĢħãģ«
    0.07
    æĻĤåĢĻ
    0.07
    ãĢħãģ®
    0.07
     ÑĢода
    0.07
    race
    0.07
    Activations Density 0.185%

    No Known Activations