© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21779
    Prev
    Next
    INDEX
    Explanations

    or, and, possibly, even

    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
    åı¦å¤ĸä¸Ģ个
    -0.10
    åı¦ä¸Ģç§į
    -0.09
    libraries
    -0.09
    ibs
    -0.08
    ück
    -0.08
    æĪ³
    -0.08
    -story
    -0.08
    山寨
    -0.08
    ç»ıå¼Ģ
    -0.08
    è¦ģåģļ好
    -0.08
    POSITIVE LOGITS
    çĶļèĩ³
    0.45
    çĶļèĩ³æĺ¯
    0.37
    çĶļèĩ³è¿ĺ
    0.34
     sogar
    0.32
     even
    0.32
     даже
    0.29
     tháºŃm
    0.29
    even
    0.29
    ä¹ĥèĩ³
    0.27
    çĶļèĩ³è¿ŀ
    0.26
    Activations Density 0.069%

    No Known Activations