© 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. 5271
    Prev
    Next
    INDEX
    Explanations

    in fact

    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
    åį´è¢«
    -0.10
     nevertheless
    -0.10
    åĵģä½į
    -0.10
     zwar
    -0.09
     nonetheless
    -0.09
    èĻ½è¯´
    -0.09
    çĵ®
    -0.09
    åį´ä¸į
    -0.09
    :inline
    -0.09
    飨
    -0.09
    POSITIVE LOGITS
    åı¯ä»¥è¯´æĺ¯
    0.12
    å°±è¿ŀ
    0.11
    åı¯ä»¥è¯´
    0.10
    æĹ©åľ¨
    0.10
    è¿Ļä¹Łæĺ¯
    0.10
    è¿Ļæĺ¯æĪij
    0.09
    æľ¬èº«å°±æĺ¯
    0.09
    使ä¹ĭ
    0.09
    æľīçĤ¹
    0.09
    éĢł
    0.08
    Activations Density 0.027%

    No Known Activations