© 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. 50335
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols followed by words

    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
    è°ĥæķ´å¥½
    -0.08
    å¯Ł
    -0.08
     –**
    -0.07
    ä¿ĿæĬ¤å¥½
    -0.07
    ukkan
    -0.07
     Ingram
    -0.07
    azon
    -0.07
     |:
    -0.07
    katan
    -0.07
    /temp
    -0.07
    POSITIVE LOGITS
    ES
    0.07
    usser
    0.07
    enthal
    0.06
    ('').
    0.06
    .poly
    0.06
    å¸ĤåĮº
    0.06
     Padahal
    0.06
    æŃ¥æŃ¥
    0.06
    unner
    0.06
     <![
    0.06
    Activations Density 0.002%

    No Known Activations