© 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. 26241
    Prev
    Next
    INDEX
    Explanations

    introductory clauses with 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
    ApplicationBuilder
    -0.08
    ä¹Łéĥ½æĺ¯
    -0.07
     Pard
    -0.07
    éĥ½ä¸įæĺ¯
    -0.07
    ska
    -0.07
    }/{
    -0.07
    (vars
    -0.07
    imore
    -0.07
    ãĤĴçµĮãģ¦
    -0.07
    _keywords
    -0.07
    POSITIVE LOGITS
    (s
    0.11
    åı«åģļ
    0.09
    ss
    0.09
    åı«
    0.08
    sWith
    0.08
    们çļĦ
    0.08
    æĪĸå¤ļ个
    0.08
    edia
    0.08
    anten
    0.08
    åĢijçļĦ
    0.07
    Activations Density 0.599%

    No Known Activations