© 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. 48746
    Prev
    Next
    INDEX
    Explanations

    bowling, serve, pace

    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
    æĻĶ
    -0.12
    家éŨåı£
    -0.10
    ä¸Ģ个个
    -0.09
    åIJ¸æĶ¶
    -0.09
    äºĨä¸Ģåľº
    -0.09
    åIJ¸
    -0.09
    èĢĻ
    -0.09
    éĢIJ
    -0.09
    ERV
    -0.08
    weise
    -0.08
    POSITIVE LOGITS
    æ²ĵ
    0.09
    ìį¨
    0.09
    inton
    0.08
     alo
    0.08
    çĬĢ
    0.08
    æ²īéĩį
    0.08
    iking
    0.08
    rack
    0.08
    ç»ĻåĪ«äºº
    0.08
    æŀ¶åŃIJ
    0.08
    Activations Density 0.007%

    No Known Activations