© 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. 10452
    Prev
    Next
    INDEX
    Explanations

    attacks, disease, rain, wives

    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
    è¡įçĶŁåĵģ
    -0.07
    AndGet
    -0.07
    hausen
    -0.07
    å«£
    -0.07
     Madden
    -0.07
    ucher
    -0.07
    çĤºæŃ¢
    -0.07
    åħ¨éĿ¢å®ĮæĪIJ
    -0.07
    ä¸ĭåIJĮ
    -0.07
    imensional
    -0.06
    POSITIVE LOGITS
    ä¹Łæľīåı¯èĥ½
    0.10
    çļĦåı¯èĥ½æĢ§
    0.09
    éĥ½æľīåı¯èĥ½
    0.08
    ä¹Łåı¯èĥ½
    0.08
     albeit
    0.07
    inski
    0.07
    åīįæıIJæĺ¯
    0.07
    åı¯èĥ½æĢ§
    0.07
    åıĸåĨ³äºİ
    0.07
    åıªè¦ģæľī
    0.07
    Activations Density 0.018%

    No Known Activations