© 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. 9823
    Prev
    Next
    INDEX
    Explanations

    č

    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
    angler
    -0.08
     Westbrook
    -0.08
    åIJ¦
    -0.07
    åľĪ
    -0.07
    éra
    -0.07
    mund
    -0.07
    oard
    -0.06
    escu
    -0.06
    gress
    -0.06
    马ä¸Ĭ
    -0.06
    POSITIVE LOGITS
    CTS
    0.08
    oczy
    0.08
    olu
    0.08
    opp
    0.07
    à¹Īาà¸Ļ
    0.07
    oplay
    0.07
    oll
    0.07
    ocomplete
    0.07
    quen
    0.07
     непов
    0.07
    Activations Density 0.258%

    No Known Activations