© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57093
    Prev
    Next
    INDEX
    Explanations

    stretching and flexibility exercises

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bas
    -0.09
    æľªç»ıæİĪæĿĥ
    -0.09
    LT
    -0.09
    éĢ®
    -0.09
    ä½ĵè´¨
    -0.09
    Tro
    -0.09
    orest
    -0.08
    леж
    -0.08
    æIJ¬è¿IJ
    -0.08
    beat
    -0.08
    POSITIVE LOGITS
    ÑĢаб
    0.09
     ris
    0.09
    å°½
    0.09
    prep
    0.08
     СеÑĢ
    0.08
    ening
    0.08
    Difference
    0.08
    åįģåħ«å±Ĭ
    0.08
    æĿª
    0.08
     öz
    0.08
    Activations Density 0.011%

    No Known Activations