© 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. 37647
    Prev
    Next
    INDEX
    Explanations

    directional movement or transition

    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
    æīįç®Ĺ
    -0.07
    以åıĬå¦Ĥä½ķ
    -0.07
    è¿ĺæĺ¯åľ¨
    -0.07
    å°±æĺ¯éĢļè¿ĩ
    -0.07
    æĪĸå°ij
    -0.07
    umn
    -0.07
     sowie
    -0.07
     ÐĿаÑĥ
    -0.07
    åĨįéĢļè¿ĩ
    -0.07
    ansk
    -0.06
    POSITIVE LOGITS
    并
    0.10
    並
    0.09
    riers
    0.09
     ÑĩÑĤобÑĭ
    0.09
    并以
    0.09
    并ä¸İ
    0.09
     Ñīоб
    0.09
    并对
    0.08
     Äijá»ĥ
    0.08
    å¹¶åľ¨
    0.08
    Activations Density 0.607%

    No Known Activations