© 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. 44779
    Prev
    Next
    INDEX
    Explanations

    decreasing levels or control

    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
    Negative Logits
    UGE
    -0.07
    ä¸įå¼ĥ
    -0.07
    æī¬
    -0.07
    å¿ĥå¾Ĺ
    -0.07
    åħĥé¦ĸ
    -0.07
    ORIZ
    -0.06
    acha
    -0.06
    uge
    -0.06
    enty
    -0.06
    bedingt
    -0.06
    POSITIVE LOGITS
     ability
    0.09
    æľīä»»ä½ķ
    0.09
    åĨį继ç»Ń
    0.09
     fucks
    0.08
    çĶļèĩ³æĺ¯
    0.08
    icom
    0.08
    /no
    0.07
     khả
    0.07
    æıIJä¾Ľä»»ä½ķ
    0.07
     altogether
    0.07
    Activations Density 0.268%

    No Known Activations