© 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. 37453
    Prev
    Next
    INDEX
    Explanations

    flexibility and stretchability

    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
    æ¸ħæ¸ħæ¥ļæ¥ļ
    -0.07
    è½°
    -0.07
    éĽĦ
    -0.07
    /cache
    -0.07
    å¿Ļ
    -0.07
    æ·Ĩ
    -0.07
    麻çĥ¦
    -0.07
    ä»ĵ
    -0.06
    åĿª
    -0.06
    æ¸ħæŃ£
    -0.06
    POSITIVE LOGITS
    /stretch
    0.15
    æŁĶ软
    0.13
    æŁĶ
    0.13
    หยุà¹Īà¸Ļ
    0.12
    elastic
    0.12
    æŁĶè»Ł
    0.12
     elasticity
    0.12
     flexibility
    0.12
    -flex
    0.11
     elastic
    0.11
    Activations Density 0.042%

    No Known Activations