© 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. 18288
    Prev
    Next
    INDEX
    Explanations

    Possible Duplicate

    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
    åı«
    -0.07
     (
    -0.07
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    -0.07
    åIJĮä¸Ģ
    -0.07
    åĩĿèģļ
    -0.06
    åħ·æľī以ä¸ĭ
    -0.06
    oret
    -0.06
    åĽłæŃ¤åľ¨
    -0.06
    ç¥
    -0.06
    å§ij
    -0.06
    POSITIVE LOGITS
    Lastly
    0.11
     Finally
    0.10
     finally
    0.10
    æľĢåIJİ
    0.10
    åIJĮæĹ¶ä¹Łè¦ģ
    0.10
     Lastly
    0.10
     schlieÃŁlich
    0.10
    åIJĮæŶè¦ģ
    0.10
    æľĢå¾Į
    0.10
    æĪijè¿ĺè¦ģ
    0.09
    Activations Density 0.008%

    No Known Activations