© 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. 16968
    Prev
    Next
    INDEX
    Explanations

    slide, hit, push, shot, extraction

    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¿Ļä¹Ī说
    -0.10
    è¿Ļæł·è¯´
    -0.10
    åıĤåĬł
    -0.10
    è¿ĺæĥ³
    -0.10
    åħ¼
    -0.10
    åľ¨çĶŁæ´»ä¸Ń
    -0.09
    èĬĤ缮ä¸Ń
    -0.09
    à¹Ģà¸ĸ
    -0.09
    åıĥåĬł
    -0.09
    说è¿ĩ
    -0.09
    POSITIVE LOGITS
    è·Łè¿Ľ
    0.09
    éļıåIJİ
    0.09
     ath
    0.09
    åIJİç»Ń
    0.09
     sco
    0.08
    æŃ£å¥½
    0.08
    æĭ³
    0.08
    å¡į
    0.08
     subsequently
    0.08
    exion
    0.08
    Activations Density 0.014%

    No Known Activations