© 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. 17817
    Prev
    Next
    INDEX
    Explanations

    gymnastics and injuries

    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
    Licensed
    -0.10
    cÃŃ
    -0.10
     اÙĦÙĨÙĤ
    -0.09
    ulet
    -0.09
    ticker
    -0.09
    æĦŁ
    -0.09
     Phil
    -0.09
    uffed
    -0.09
    身åIJİ
    -0.09
    ä¸ĢåĪ»
    -0.09
    POSITIVE LOGITS
     gymn
    0.10
    åĬ¨ä½ľ
    0.10
    æŀ¶
    0.09
    妩
    0.09
    è§ħ
    0.08
    è°İè¨Ģ
    0.08
    ä¼ĺç¾İ
    0.08
     KC
    0.08
    èĭŁ
    0.08
     acl
    0.08
    Activations Density 0.072%

    No Known Activations