© 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. 32730
    Prev
    Next
    INDEX
    Explanations

    even or something

    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¦ģä¹Ī
    -0.10
    è¦ģä¹Īæĺ¯
    -0.09
    åıĪ说
    -0.09
    either
    -0.09
     Ø¥Ùħا
    -0.09
     entweder
    -0.08
     either
    -0.08
    åıĪä¸Ģ
    -0.08
    æľīä¸ĭåĪĹ
    -0.08
    ither
    -0.08
    POSITIVE LOGITS
    à¹Ģลยà¸Ĺีà¹Ģà¸Ķียว
    0.13
     sogar
    0.13
    çĶļèĩ³æĺ¯
    0.11
    çĶļèĩ³åı¯ä»¥
    0.11
     even
    0.11
    ãģĻãĤī
    0.11
     downright
    0.11
    çĶļèĩ³
    0.11
     addirittura
    0.11
     persino
    0.11
    Activations Density 0.382%

    No Known Activations