© 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. 55754
    Prev
    Next
    INDEX
    Explanations

    diving and swimming

    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
    æĭ¨
    -0.08
    è·Łéļı
    -0.08
     ÐĶе
    -0.08
    _DLL
    -0.08
    ç±
    -0.08
    inkle
    -0.08
    éģ
    -0.08
     somewhere
    -0.08
    éĢĤ
    -0.08
     Madden
    -0.08
    POSITIVE LOGITS
    æ³³
    0.12
    æ½ľæ°´
    0.11
     swim
    0.11
    æ³īæ°´
    0.10
    游泳
    0.10
     blue
    0.10
     swims
    0.10
    ä¹ĭä¸ĭ
    0.09
    çĥŃæ°´
    0.09
     Clay
    0.09
    Activations Density 0.077%

    No Known Activations