© 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. 4157
    Prev
    Next
    INDEX
    Explanations

    closing punctuation or 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
    aison
    -0.08
    ãĥ¬ãĥ«
    -0.08
     Aran
    -0.07
    äºļæ´²æĿ¯
    -0.07
    ikker
    -0.07
    colm
    -0.07
    <|im_start|>
    -0.07
     |(
    -0.07
    aeda
    -0.07
     ÐijÑĢÑİ
    -0.07
    POSITIVE LOGITS
    æĸĩç«łæłĩçŃ¾
    0.09
    ì¶Ķ
    0.07
    iw
    0.06
    ä½łèĩªå·±çļĦ
    0.06
    åīįæľŁ
    0.06
     Ñĥб
    0.06
    TextNode
    0.06
    æ²ī
    0.06
    缼
    0.06
    ha
    0.06
    Activations Density 0.009%

    No Known Activations