© 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. 64967
    Prev
    Next
    INDEX
    Explanations

    negative sentiment or 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
    åıªåı¯æĥľ
    -0.08
    bauer
    -0.07
     sayesinde
    -0.07
    ÙĪار
    -0.07
    OrCreate
    -0.07
    ottie
    -0.07
     Niestety
    -0.07
    pn
    -0.07
    aign
    -0.07
     battered
    -0.07
    POSITIVE LOGITS
     ÐĹаÑĤо
    0.14
    ä½Ĩåı¯ä»¥
    0.13
     Worse
    0.12
     :(
    0.12
    è¿ĺä¸įå¦Ĥ
    0.11
     заÑĤо
    0.11
    ä½Ĩåıªè¦ģ
    0.10
     worse
    0.10
    尽管å¦ĤæѤ
    0.10
    éĻ¤éĿŀ
    0.09
    Activations Density 0.547%

    No Known Activations