© 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. 29670
    Prev
    Next
    INDEX
    Explanations

    modified conditions or quantities

    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
     drastically
    -0.09
     devastating
    -0.09
     terrible
    -0.09
    æł¹æľ¬æĹłæ³ķ
    -0.08
    ç»ĿæľĽ
    -0.08
     horrible
    -0.08
    æł¹æľ¬æ²¡æľī
    -0.08
    ç»Ŀå¢ĥ
    -0.08
     dramatically
    -0.08
    æ··ä¹±
    -0.08
    POSITIVE LOGITS
    çķ¥æĺ¾
    0.16
     somewhat
    0.16
     slightly
    0.14
     некоÑĤоÑĢ
    0.14
    äºĽè®¸
    0.13
    çķ¥æľī
    0.13
    æľīäºĽä¸į
    0.13
    è¿ĺæĺ¯æľīäºĽ
    0.13
    åŃĺåľ¨ä¸Ģå®ļçļĦ
    0.13
     slight
    0.12
    Activations Density 0.316%

    No Known Activations