© 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. 1301
    Prev
    Next
    INDEX
    Explanations

    years before invention

    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
    rf
    -0.09
    空åĨĽ
    -0.09
    çļĦä¸ĢéĿ¢
    -0.09
    è¾¹ç¼ĺ
    -0.08
    buzz
    -0.08
    æĢ»éĺŁ
    -0.08
    æģĭ
    -0.08
    æĪijèĩªå·±
    -0.08
    çĭŃ
    -0.08
    è°Īè¯Ŀ
    -0.08
    POSITIVE LOGITS
    éĩį伤
    0.10
    åħ¥åľº
    0.10
    ús
    0.09
    ç²¾
    0.09
    åĪ¶
    0.09
    eah
    0.09
    åĵ¥ä¼¦æ¯Ķäºļ
    0.09
    åįİå°Ķ
    0.09
    _DIRS
    0.09
     инÑĤеÑĢеÑģ
    0.08
    Activations Density 0.195%

    No Known Activations