© 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. 27300
    Prev
    Next
    INDEX
    Explanations

    gymnastics related terms

    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
    -0.09
    ving
    -0.09
     Shank
    -0.09
    é¹Ħ
    -0.08
     LOC
    -0.08
    æ¾İ
    -0.08
    èĽĭ
    -0.08
    кеÑĢ
    -0.08
    缮åħī
    -0.08
    cie
    -0.08
    POSITIVE LOGITS
    astics
    0.10
    æİĩ
    0.09
    ä¸ºæľŁ
    0.09
    æĿ·
    0.09
    ÑģоÑģ
    0.08
    aras
    0.08
    çĶ¨åĵģ
    0.08
    è°ķ
    0.08
    nas
    0.08
    榻
    0.08
    Activations Density 0.010%

    No Known Activations