© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12260
    Prev
    Next
    INDEX
    Explanations

    The good news

    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
    Negative Logits
    ä¹ĥèĩ³
    -0.09
    ÑĢÑĥÑĤ
    -0.09
    çĢļ
    -0.09
    ald
    -0.09
    ç¼Ł
    -0.09
    ä¸Ģå¤Ħ
    -0.09
    zie
    -0.08
    èĩ³åħ³
    -0.08
    为ä»Ģä¹Īè¦ģ
    -0.08
    AKER
    -0.08
    POSITIVE LOGITS
    ä¸įçĶ¨æĭħå¿ĥ
    0.10
    æĪijåıijçİ°
    0.10
    æĪijè¿ĺ
    0.09
    å©¿
    0.09
     ngắn
    0.09
    åħįéĻ¤
    0.09
    è¿ĺæľīå¾Īå¤ļ
    0.08
    æľīåħ³éĥ¨éŨ
    0.08
     sm
    0.08
    ä¸Ĭåı¸
    0.08
    Activations Density 0.047%

    No Known Activations