© 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. 16097
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols

    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
    erts
    -0.07
    éģIJ
    -0.06
    ulton
    -0.06
    严谨
    -0.06
    就好æ¯Ķ
    -0.06
    åĪĨéħįåĪ°
    -0.06
    ree
    -0.06
    åıĸ
    -0.06
     Partition
    -0.06
    elos
    -0.06
    POSITIVE LOGITS
     Unicode
    0.09
    åĮºåĪ«äºİ
    0.08
    inox
    0.08
    Unicode
    0.08
    æł·å¼ı
    0.08
    åľ°å¤´
    0.07
    æłĩåĩĨ
    0.07
     replacements
    0.07
    _STANDARD
    0.07
    çļĦæłĩåĩĨ
    0.07
    Activations Density 0.010%

    No Known Activations