© 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. 37582
    Prev
    Next
    INDEX
    Explanations

    summary or tl;dr

    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
    elaar
    -0.09
     PRESID
    -0.09
    游åĪĥ
    -0.08
    ìĸ´ëĵľ
    -0.08
    esty
    -0.08
    书ç½ij
    -0.08
    ä¼¼ä¹İä¹Ł
    -0.08
    croft
    -0.08
    ologe
    -0.08
    ilia
    -0.08
    POSITIVE LOGITS
    以æľĢ
    0.07
     summary
    0.07
    :
    0.07
    esting
    0.07
    cher
    0.06
    summary
    0.06
     Summary
    0.06
    ç»·ç´§
    0.06
    æ¡ĤåĨł
    0.06
    ä¸ĭ次
    0.06
    Activations Density 0.002%

    No Known Activations