© 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. 11938
    Prev
    Next
    INDEX
    Explanations

    scientific publication titles

    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
    chan
    -0.07
    ä»
    -0.06
     chan
    -0.06
    xp
    -0.06
    anced
    -0.06
    ниÑģ
    -0.06
     Sat
    -0.06
     gär
    -0.06
    .generated
    -0.06
    踩
    -0.06
    POSITIVE LOGITS
    .spring
    0.08
    à¸Ĥà¸Ńà¸Ķ
    0.08
    Ĩµ
    0.08
    lech
    0.08
    _ratio
    0.07
    Ù°
    0.07
    ymb
    0.07
    bruck
    0.07
     Lon
    0.07
    æĺ¥æĿ¥
    0.07
    Activations Density 0.010%

    No Known Activations