© 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. 39608
    Prev
    Next
    INDEX
    Explanations

    First of all

    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
    ting
    -0.08
    çĦ¶åIJİåıĪ
    -0.07
    ukk
    -0.07
    antai
    -0.07
    è¿Ļæł·å°±åı¯ä»¥
    -0.07
    .literal
    -0.07
    çĶļèĩ³ä¼ļ
    -0.07
    å¾Ĺ天
    -0.07
    ifr
    -0.07
    å±ĤçļĦ
    -0.07
    POSITIVE LOGITS
    adays
    0.07
    oloc
    0.07
    åĽŀ顾
    0.07
    zien
    0.07
    ä¿Ĺè¯Ŀ说
    0.07
    orium
    0.06
    ä»Ģä¹Īæĺ¯
    0.06
    review
    0.06
     consider
    0.06
    æ¦ľ
    0.06
    Activations Density 0.001%

    No Known Activations