© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10746
    Prev
    Next
    INDEX
    Explanations

    programming language implementations

    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
    hoff
    -0.07
    auh
    -0.07
    ocha
    -0.06
    readystatechange
    -0.06
    KeyName
    -0.06
    aud
    -0.06
    ulaires
    -0.06
    ä¹ĥ
    -0.06
     AOL
    -0.06
    aur
    -0.06
    POSITIVE LOGITS
     version
    0.09
     translation
    0.09
    ä¸Ĭåij¨
    0.08
    amentos
    0.08
    _version
    0.08
    诧
    0.07
    çīĪæľ¬çļĦ
    0.07
     equivalent
    0.07
     translations
    0.07
    ç¿»è¯ij
    0.07
    Activations Density 0.089%

    No Known Activations