© 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. 21493
    Prev
    Next
    INDEX
    Explanations

    does not mean

    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
     brid
    -0.09
    é£ĺ
    -0.09
    åIJİæŀľ
    -0.08
    æ¯Ķè¾ĥ
    -0.08
    å¼Ĭ
    -0.08
    æĥħ
    -0.08
    æľĢå¿«
    -0.08
    Ter
    -0.08
    iid
    -0.08
    TRL
    -0.08
    POSITIVE LOGITS
    并ä¸į代表
    0.23
    ä¸į代表
    0.23
    并ä¸įæĦıåij³
    0.22
    æĦıåij³çĿĢ
    0.21
    ä¸įä¸Ģå®ļ
    0.15
     means
    0.15
    并ä¸įæĺ¯
    0.15
    Means
    0.14
    并ä¸į
    0.14
    并éĿŀ
    0.13
    Activations Density 0.061%

    No Known Activations