© 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. 65499
    Prev
    Next
    INDEX
    Explanations

    nearest integer

    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
     exactly
    -0.09
     ÑĢовно
    -0.08
    æĹłæķ°
    -0.08
     strictly
    -0.08
     infinitely
    -0.07
     infinit
    -0.07
     precisely
    -0.07
     accom
    -0.07
    ä¹Ŀ天
    -0.07
     exact
    -0.07
    POSITIVE LOGITS
    大æ¦Ĥåľ¨
    0.10
    ç²Ĺçķ¥
    0.10
     roughly
    0.09
    估计
    0.09
     ballpark
    0.09
    缸è¿ij
    0.09
    ä¼°ç®Ĺ
    0.08
    大èĩ´
    0.08
     cercano
    0.08
    ä¼°è¨Ī
    0.08
    Activations Density 0.001%

    No Known Activations