© 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. 10745
    Prev
    Next
    INDEX
    Explanations

    foreign characters and math notation

    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
    য়ার
    -0.07
     заÑĤо
    -0.07
    veral
    -0.07
    BOR
    -0.07
    ERAL
    -0.06
    awn
    -0.06
    _leader
    -0.06
    edig
    -0.06
    vent
    -0.06
    TERN
    -0.06
    POSITIVE LOGITS
    ä¸įåı¯æĢĿè®®
    0.09
    身临åħ¶å¢ĥ
    0.08
    æ¯Ľæ³½ä¸ľ
    0.07
    اÙĤ
    0.07
    åĴĮæľīåħ³
    0.07
    emet
    0.07
    ablish
    0.07
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.07
    .bootstrapcdn
    0.07
    æѤçĶŁ
    0.07
    Activations Density 0.015%

    No Known Activations