© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 60208
    Prev
    Next
    INDEX
    Explanations

    punctuation or operators

    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
    _REPLACE
    -0.08
    gone
    -0.07
    gary
    -0.07
    achine
    -0.07
    ç«¥
    -0.07
    ä»»
    -0.06
    å¿ĥå®ī
    -0.06
    æ°´åİĭ
    -0.06
    éķľ
    -0.06
    AGIC
    -0.06
    POSITIVE LOGITS
    _SEP
    0.08
    解读
    0.08
    _SEPARATOR
    0.08
    åĪĨå¼Ģ
    0.08
     parenthesis
    0.08
     parentheses
    0.08
     comma
    0.08
    éĢĹåı·
    0.08
    æķ´ä½ĵçļĦ
    0.08
     paren
    0.08
    Activations Density 0.135%

    No Known Activations