© 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. 23271
    Prev
    Next
    INDEX
    Explanations

    end punctuation or control sequences

    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
    unread
    -0.07
    ÑĤÑİ
    -0.06
    sy
    -0.06
    åįķ
    -0.06
    ä¹°åįķ
    -0.06
    ä¸Ģåľ°
    -0.06
     Guer
    -0.06
    logs
    -0.06
    ano
    -0.06
    ä¸Ģ缮
    -0.06
    POSITIVE LOGITS
    ariato
    0.08
    áĥĶáĥķ
    0.07
     Horton
    0.07
    hés
    0.07
     Pound
    0.07
    ALSE
    0.07
     Ore
    0.07
    å¿ĺæĢĢ
    0.07
    dre
    0.07
    bauer
    0.07
    Activations Density 0.012%

    No Known Activations