© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44870
    Prev
    Next
    INDEX
    Explanations

    closing 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
    Ñĭл
    -0.07
     subscribed
    -0.07
    è¾¾æĸ¯
    -0.07
    çļĦè§ĦåĪĻ
    -0.06
     herself
    -0.06
    æĹłäºĭ
    -0.06
    sson
    -0.06
    å¤ĸçĶ¨
    -0.06
    详è§ģéĻĦ件
    -0.06
    ursa
    -0.06
    POSITIVE LOGITS
    loon
    0.08
     ratios
    0.08
    åį¡è·¯
    0.08
    appa
    0.07
     chô
    0.07
    èĩªçĦ¶èĢĮ
    0.07
    éĻ
    0.07
    oplan
    0.07
    ongi
    0.07
    ¬
    0.07
    Activations Density 0.011%

    No Known Activations