© 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. 657
    Prev
    Next
    INDEX
    Explanations

    counts different

    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
    artig
    -0.08
    adu
    -0.08
    æĻĵ
    -0.08
    etter
    -0.07
    asthan
    -0.07
    etlen
    -0.07
    à¥Ī
    -0.07
    ער
    -0.07
    bung
    -0.07
    anke
    -0.07
    POSITIVE LOGITS
    ä¹Łç®Ĺ
    0.16
    èĻ½çĦ¶ä¸įæĺ¯
    0.12
    ä¹Łç®Ĺæĺ¯
    0.10
    çħ§æł·
    0.10
    ä¸įç®Ĺ
    0.10
    åıªè¦ģèĥ½
    0.10
     counts
    0.09
    éĤ£ä¹Łæĺ¯
    0.09
    åıªè¦ģæĺ¯
    0.09
    ä»įåı¯
    0.09
    Activations Density 0.093%

    No Known Activations