© 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. 37452
    Prev
    Next
    INDEX
    Explanations

    options, services, programs

    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
    åħ¨æĹ¥
    -0.10
    è¿Ļæī¹
    -0.09
    èµ·åºĬ
    -0.09
    ä¸įç»ı
    -0.08
    æĪijæīį
    -0.08
     Liberal
    -0.08
    éĺ¿æĭī伯
    -0.08
    åİ»è¿ĩ
    -0.08
    ÙĨت
    -0.08
    åıªçŁ¥éģĵ
    -0.08
    POSITIVE LOGITS
    æľī许å¤ļ
    0.14
    æľīå¾Īå¤ļç§į
    0.11
    线ä¸Ĭ
    0.10
    æľīå¾Īå¤ļ
    0.10
    åı¯ä»¥å¸®åĬ©
    0.10
    ç§įç±»
    0.10
    ç·ļä¸Ĭ
    0.10
    éĥ½åı¯ä»¥
    0.09
    å¾Ģå¾Ģ
    0.09
    éĥ½æľī
    0.09
    Activations Density 0.106%

    No Known Activations