© 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. 63312
    Prev
    Next
    INDEX
    Explanations

    a followed by sports or action words

    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
    è´¢åĬĽ
    -0.10
    麸
    -0.10
    DDS
    -0.10
    çļĦä¸ĢéĿ¢
    -0.09
    æ¯ı次éĥ½
    -0.09
    éĶĪ
    -0.09
    棺
    -0.09
    ä¹ĭ人
    -0.09
    åĨµä¸Ķ
    -0.09
    è§ī
    -0.09
    POSITIVE LOGITS
     иÑģп
    0.09
    éĩįè¦ģ
    0.09
    reso
    0.09
    .criteria
    0.08
     admir
    0.08
    âĹĤ
    0.08
     mend
    0.08
    è¿ŀ
    0.08
     thừa
    0.08
    é«ĺ级
    0.08
    Activations Density 0.015%

    No Known Activations