© 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. 48281
    Prev
    Next
    INDEX
    Explanations

    numbers followed by currency or punctuation

    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
    ä¸Ĭè¿Ľå¿ĥ
    -0.08
    endis
    -0.08
     Glob
    -0.08
    inha
    -0.08
    泡èĮ¶
    -0.08
    alani
    -0.08
    第ä¸Ģ人æ°ijåĮ»éĻ¢
    -0.08
    Glob
    -0.08
    æIJı
    -0.08
    chá
    -0.08
    POSITIVE LOGITS
    ucken
    0.08
     mult
    0.07
    ince
    0.07
    èģļ
    0.07
    èµ·èĪª
    0.06
     poly
    0.06
     enough
    0.06
    TypeInfo
    0.06
    空港
    0.06
    ssa
    0.06
    Activations Density 0.018%

    No Known Activations