© 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. 55051
    Prev
    Next
    INDEX
    Explanations

    increased / higher / scores / recurrence / selection / resemblance

    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
     strictly
    -0.08
     completely
    -0.07
    _pow
    -0.07
    åĶ¯ä¸ĢçļĦ
    -0.07
    å®Įåħ¨
    -0.07
     suf
    -0.07
    toy
    -0.07
    æľĢæł¹æľ¬
    -0.06
    çļĦåĶ¯ä¸Ģ
    -0.06
     cleanly
    -0.06
    POSITIVE LOGITS
    erness
    0.09
    åĤ¾åIJij
    0.09
    åĢ¾åIJijäºİ
    0.09
    entially
    0.08
     scores
    0.08
    é«ĺ人
    0.08
    åģļèµ·æĿ¥
    0.08
    mapped
    0.08
    æľĪçĶŁ
    0.08
    çĽ¸å¯¹çļĦ
    0.08
    Activations Density 0.071%

    No Known Activations