© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8249
    Prev
    Next
    INDEX
    Explanations

    what is

    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
    ough
    -0.09
    æĹ©æĻļ
    -0.09
    ç¡®
    -0.09
    ä¸ĢåĪĩéĥ½
    -0.09
    vä
    -0.08
    IRD
    -0.08
    æ°´åĪĨ
    -0.08
    éĻĨ
    -0.08
    è¿ĺæĺ¯
    -0.08
    ä¸ĢåĪĻ
    -0.08
    POSITIVE LOGITS
    åĽŀäºĭ
    0.11
    ä¸ĢåĽŀäºĭ
    0.10
    æľ¬è´¨
    0.10
    ä»Ģä¹Īæĺ¯
    0.10
     meant
    0.10
    èĩ¾
    0.10
    å¹¶åľ¨
    0.09
    å®ŀè´¨æĢ§
    0.09
    æ®ī
    0.09
    æĦıåij³çĿĢ
    0.09
    Activations Density 0.105%

    No Known Activations