© 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. 44019
    Prev
    Next
    INDEX
    Explanations

    operators and symbols

    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
    ä¸į计
    -0.08
    âĢij
    -0.07
    ovich
    -0.06
    —
    -0.06
     defined
    -0.06
     (
    -0.06
     determined
    -0.06
    ä¹ŁæŃ£æĺ¯
    -0.06
    -0.06
    礼è²Į
    -0.06
    POSITIVE LOGITS
    Accessor
    0.09
    åºĶè¯¥åľ¨
    0.08
    åı¯ä»¥çĶ¨
    0.08
    nire
    0.08
     thankfully
    0.08
     #=>
    0.08
     diminu
    0.08
    æĬķèµĦæĪĸ
    0.08
    `\
    0.08
     easiest
    0.08
    Activations Density 0.002%

    No Known Activations