© 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. 28872
    Prev
    Next
    INDEX
    Explanations

    usually, have, be verbs

    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
    没æľīåħ³ç³»
    -0.08
     nhau
    -0.08
    ild
    -0.08
    æīĵèµ¢
    -0.08
    åıªæıIJä¾Ľ
    -0.08
    ä»ħ代表
    -0.07
    åıĤä¸İæ´»åĬ¨
    -0.07
    .contents
    -0.07
    ngthen
    -0.07
    .checked
    -0.07
    POSITIVE LOGITS
     either
    0.08
    å°±åľ¨
    0.08
     somewhere
    0.08
    ä¸įä¼ļæĺ¯
    0.07
    å°±åľ¨è¿Ļ
    0.07
    èĬ±èIJ½
    0.07
    ä¸Ģå®ļæĺ¯
    0.07
    åľ¨äºİ
    0.07
     among
    0.07
    either
    0.07
    Activations Density 0.026%

    No Known Activations