© 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. 64216
    Prev
    Next
    INDEX
    Explanations

    everything starts somewhere

    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
    俨çĦ¶
    -0.08
    åħ¨ç¨ĭ
    -0.08
     faudra
    -0.08
    ãģ£ãģĿ
    -0.07
    ä¾ĿçĦ¶æĺ¯
    -0.07
    æĬĺä¸įæī£
    -0.07
    ä¸įæĬĺä¸įæī£
    -0.07
     sequer
    -0.07
    赫çĦ¶
    -0.07
    ä¹ĭéģ¥
    -0.07
    POSITIVE LOGITS
    æľīæŶåĢĻ
    0.11
     sometimes
    0.10
    æľīçļĦæŶåĢĻ
    0.10
    è´µåľ¨
    0.09
    æľīæŶ
    0.09
    æĢ»æĺ¯åľ¨
    0.09
    æĢ»æľī
    0.09
    sometimes
    0.09
    æľīäºĽäºĭæĥħ
    0.09
     Sometimes
    0.09
    Activations Density 0.386%

    No Known Activations