© 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. 2384
    Prev
    Next
    INDEX
    Explanations

    files or code paths

    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
    éĹŃä¸Ĭ
    -0.06
    tml
    -0.06
    ++++++++
    -0.06
     accompanying
    -0.06
    +/
    -0.06
    ute
    -0.06
    PTS
    -0.06
    ÑĦоÑĢ
    -0.06
    ino
    -0.06
    ä¼´
    -0.06
    POSITIVE LOGITS
    otov
    0.08
    ÙijÙĩ
    0.07
    ä¸įèĻļ
    0.07
    ashes
    0.07
    itives
    0.07
     (?
    0.07
    atique
    0.07
    otar
    0.07
    undred
    0.07
    -football
    0.07
    Activations Density 0.317%

    No Known Activations