© 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. 55209
    Prev
    Next
    INDEX
    Explanations

    check out, receive, collect

    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
    åĬ²
    -0.08
    æı´
    -0.07
    ë¥
    -0.07
     unary
    -0.07
    æ°ij建
    -0.07
     kans
    -0.07
    奢
    -0.07
    ìĸ´ëĤĺ
    -0.07
    产åĵģåı¬åĽŀ
    -0.07
    à®®à¯įப
    -0.07
    POSITIVE LOGITS
    交æİ¥
    0.15
    移交
    0.12
    æ¸ħçĤ¹
    0.11
    éªĮæĶ¶
    0.10
    ä¿Ŀ管
    0.10
    çĻ»è®°æīĭç»Ń
    0.10
    çī©åĵģ
    0.09
    æĮĩå®ļåľ°çĤ¹
    0.09
     transferring
    0.08
    æݥ管
    0.08
    Activations Density 0.033%

    No Known Activations