© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25065
    Prev
    Next
    INDEX
    Explanations

    intellectuals like

    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
    å²ģå²ģ
    -0.07
    缸éĤ»
    -0.07
     rewarding
    -0.07
    é¦ĸå¸Ńæī§è¡Įå®ĺ
    -0.07
    å®Ļ
    -0.07
    agma
    -0.07
     TLC
    -0.07
    æ¯ıå¹´éĥ½
    -0.07
    æ¬§çĽŁ
    -0.06
    åĮĹ约
    -0.06
    POSITIVE LOGITS
     nationalists
    0.10
     nationalist
    0.09
    æ¸ħæľ«
    0.09
    è¾Ľäº¥éĿ©åij½
    0.08
     intellectuals
    0.08
     patriotic
    0.08
    çĶ·åĦ¿
    0.08
    æ°ijåĽ½
    0.08
    åįĹæ´ĭ
    0.08
    åŃĻä¸Ńå±±
    0.08
    Activations Density 0.048%

    No Known Activations