© 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. 50971
    Prev
    Next
    INDEX
    Explanations

    secondly or second

    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
    æĭ¢
    -0.10
    å´Ń
    -0.09
    缴éĢļ车
    -0.09
    ä¹Łè¢«
    -0.09
    ä¸ĢåŃĹ
    -0.09
    ä¸Ģåī¯
    -0.08
    chers
    -0.08
    åIJĮæĹ¶ä¹Ł
    -0.08
    åIJĮæľŁ
    -0.08
    è¥Ł
    -0.08
    POSITIVE LOGITS
    ä¸īæĺ¯
    0.10
    arily
    0.10
    åħ¶æ¬¡
    0.10
    æĽ´éĩįè¦ģ
    0.10
    èİ«è¿ĩäºİ
    0.09
    件äºĭ
    0.09
     importantly
    0.09
    nton
    0.09
    æĪijè¦ģ
    0.09
    song
    0.08
    Activations Density 0.033%

    No Known Activations