© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32903
    Prev
    Next
    INDEX
    Explanations

    specific identifiers or technical terms

    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
    æĪĸåħ¶ä»ĸ
    -0.12
    æĪĸåħ¶å®ĥ
    -0.11
    æĪĸèĢħåħ¶ä»ĸ
    -0.11
    æĪĸä¸İ
    -0.10
    æĪĸæľįåĬ¡
    -0.10
    æĪĸéĿŀ
    -0.10
    æĪĸåľ¨
    -0.10
    æĪĸæľª
    -0.09
    æĪĸå¤ļ
    -0.09
    æĪĸ个人
    -0.09
    POSITIVE LOGITS
    åıĬåħ¶
    0.16
    ãģ¨ãģĿãģ®
    0.12
     and
    0.11
    _and
    0.11
    åıĬéħįå¥Ĺ
    0.11
    åıĬ
    0.11
    åı·åĴĮ
    0.10
     beserta
    0.10
    &C
    0.10
    à¹ģละà¸Ħวาม
    0.10
    Activations Density 0.645%

    No Known Activations