© 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. 56319
    Prev
    Next
    INDEX
    Explanations

    image capture or recording actions

    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
    IDAD
    -0.10
    Drv
    -0.10
    urement
    -0.10
    æĪIJé¾Ļ
    -0.10
    isz
    -0.09
    usi
    -0.09
    лÑıÑĢ
    -0.09
    带æĿ¥æĽ´å¤ļ
    -0.08
    rosse
    -0.08
    èݲ
    -0.08
    POSITIVE LOGITS
    æĺ¯åľ¨
    0.10
    æľī幸
    0.09
    éļıæīĭ
    0.09
    Taken
    0.09
    éĢīæĭ
    0.09
    eller
    0.09
    çĥĪ
    0.09
    ä»Ģä¹Īåľ°æĸ¹
    0.09
    åIJĮä¸Ģ个
    0.09
    æĪijå½ĵæŶ
    0.08
    Activations Density 0.099%

    No Known Activations