© 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. 16550
    Prev
    Next
    INDEX
    Explanations

    only so much

    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
    åĪ¹
    -0.10
    çĴĭ
    -0.09
    为ä¸ŃåĽ½
    -0.09
    foy
    -0.09
    åıĮåıĮ
    -0.08
    ridged
    -0.08
    秩
    -0.08
    èĭĮ
    -0.08
    管çIJĨä¸Ńå¿ĥ
    -0.08
    æŃ£å¥½
    -0.08
    POSITIVE LOGITS
    æľīä¸Ģå®ļ
    0.11
    éĤ£ä¹Īå¤ļ
    0.10
    ä¸Ģå®ļçļĦ
    0.10
    èµ°å¾Ĺ
    0.10
    æľīå¤ļå°ij
    0.09
    è¿Ļä¹Īå¤ļ
    0.09
    å¹²åĺĽ
    0.09
    ä¹Łä¸įåı¯èĥ½
    0.09
    åĺĽ
    0.09
    æ¯ķç«Ł
    0.09
    Activations Density 0.034%

    No Known Activations