© 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. 35064
    Prev
    Next
    INDEX
    Explanations

    or and -style

    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
     رائ
    -0.07
    ÙĦاÙģ
    -0.07
    -ton
    -0.07
    asp
    -0.07
    :Any
    -0.07
    ubre
    -0.07
    ë¡ľëĤĺ
    -0.07
    å¸Ī
    -0.06
    á»Ļn
    -0.06
    å¸Ĩ
    -0.06
    POSITIVE LOGITS
    éľĢè¦ģæĪij们
    0.08
    åľ°ä¹ħ
    0.07
    andest
    0.07
    abel
    0.07
    ä¼´ä½ł
    0.07
    èļ£
    0.07
    å¸ĮæľĽæĤ¨
    0.07
    å¸ĮæľĽå¤§å®¶èĥ½å¤Ł
    0.07
    posal
    0.07
    texts
    0.06
    Activations Density 0.002%

    No Known Activations