© 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. 45363
    Prev
    Next
    INDEX
    Explanations

    sequence after 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
    iform
    -0.08
    笳
    -0.08
    æĪĸå°ij
    -0.08
    errupt
    -0.07
    oly
    -0.07
    edig
    -0.07
    æĽľ
    -0.07
    ä¸įå®ĮçļĦ
    -0.07
    lick
    -0.07
     seder
    -0.07
    POSITIVE LOGITS
    hte
    0.07
    åĨ³å®ļçĿĢ
    0.07
    çľģå§Ķ书记
    0.06
    ä¸ĢèĪ¬ä¸º
    0.06
     preserved
    0.06
    æ¸ħé¦Ļ
    0.06
    éĹ®é¢ĺ
    0.06
     notably
    0.06
    ä¸Ģ个æĺ¯
    0.06
    åıĬ管çIJĨ
    0.06
    Activations Density 0.302%

    No Known Activations