© 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. 63769
    Prev
    Next
    INDEX
    Explanations

    code punctuation and symbols

    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
    altro
    -0.07
    åĬłå¼ºåŃ¦ä¹ł
    -0.07
    wein
    -0.06
    teman
    -0.06
    itam
    -0.06
    udel
    -0.06
    enor
    -0.06
    ÑĤÑĢÑĥ
    -0.06
    æľĭ
    -0.06
    eden
    -0.06
    POSITIVE LOGITS
    conds
    0.08
    ÙĪارÙĩ
    0.07
    åı¯éĢīä¸Ń
    0.07
    rary
    0.07
    åİ»æĦŁåıĹ
    0.07
    avy
    0.07
    arcz
    0.07
    å¯Į
    0.07
    ç¬ijæĦı
    0.07
    owitz
    0.07
    Activations Density 0.259%

    No Known Activations