© 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. 52188
    Prev
    Next
    INDEX
    Explanations

    stereoisomers (R, S, H)

    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
    计
    -0.08
    _expand
    -0.08
     substitutes
    -0.07
    eki
    -0.07
    计çļĦ
    -0.07
    igel
    -0.06
     hun
    -0.06
    ä¸į足
    -0.06
     substitute
    -0.06
    unden
    -0.06
    POSITIVE LOGITS
    缸åıįçļĦ
    0.10
     opposite
    0.09
    è¿ŀç»ŃçļĦ
    0.09
    éķľåĥı
    0.09
    agger
    0.08
    å¿ħçĦ¶æĺ¯
    0.08
     mirrored
    0.08
     combination
    0.08
    Locked
    0.07
    mirror
    0.07
    Activations Density 0.004%

    No Known Activations