© 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. 31671
    Prev
    Next
    INDEX
    Explanations

    C-H bonds

    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
    er
    -0.10
    à¹Į
    -0.07
    al
    -0.07
    ÑģÑĮ
    -0.07
    ,
    -0.07
    ral
    -0.06
    adays
    -0.06
    nt
    -0.06
    h
    -0.06
    uu
    -0.06
    POSITIVE LOGITS
    ÏĦÏĮ
    0.08
    anax
    0.08
    å®īåħ¨è¯ĦåĪĨ
    0.08
    acus
    0.08
    代ä¼ļ
    0.08
    isso
    0.08
    पà¥Ģ
    0.08
    Ä«s
    0.08
    icino
    0.08
    áĢŃáĢ¯
    0.08
    Activations Density 0.027%

    No Known Activations