© 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. 1310
    Prev
    Next
    INDEX
    Explanations

    previous or next links

    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
    inders
    -0.08
    æľĢåIJİåľ¨
    -0.08
    æł·æł·
    -0.07
    ervis
    -0.07
    ampang
    -0.07
    æĿ¡æĿ¡
    -0.07
    è·ijåĪ°
    -0.07
    ocode
    -0.06
    йл
    -0.06
    ial
    -0.06
    POSITIVE LOGITS
    ä¸ĭä¸Ģ个
    0.14
    ä¸ĭä¸Ģ
    0.14
     next
    0.13
    ä¸ĭä¸ĢåĢĭ
    0.12
    ä¸ĭä¸ĢæĿ¡
    0.12
    next
    0.11
     nächste
    0.11
    ,next
    0.11
    ä¸ĭä¸ĢæŃ¥
    0.10
    ä¸ĭä¸Ģéĺ¶æ®µ
    0.10
    Activations Density 0.118%

    No Known Activations