© 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. 48468
    Prev
    Next
    INDEX
    Explanations

    punctuation and code delimiters

    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
    .Plugin
    -0.07
    صر
    -0.07
    çŃīå¾ħçĿĢ
    -0.06
    обоÑĢоÑĤ
    -0.06
    xdb
    -0.06
     McGu
    -0.06
    æĸĹ士
    -0.06
    epend
    -0.06
    çĦ¶åIJİåıĪ
    -0.06
    pager
    -0.06
    POSITIVE LOGITS
    imps
    0.07
    áĢ¸
    0.07
    azel
    0.07
    atte
    0.06
    .reshape
    0.06
    LOSS
    0.06
    å¤ļ大çļĦ
    0.06
    agin
    0.06
    éĺµé£İ
    0.06
     gén
    0.06
    Activations Density 0.014%

    No Known Activations