© 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. 48538
    Prev
    Next
    INDEX
    Explanations

    look or seem, and how things compare

    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¬å¤´
    -0.10
    ibus
    -0.09
    -interest
    -0.09
    èĭ¹
    -0.09
    Interest
    -0.09
    Recognition
    -0.09
    æ©«
    -0.09
    æĻĵå¾Ĺ
    -0.09
     Interest
    -0.09
    建æĪIJåIJİ
    -0.09
    POSITIVE LOGITS
    åıĭ
    0.09
    æĺ¯ä¸Ģ项
    0.09
    æĺ¾å¾Ĺ
    0.09
    好åĥı
    0.08
     cứ
    0.08
    æĻ®éĢļçļĦ
    0.08
    ä¸ºçĽ®çļĦ
    0.08
    ç¼ĵ
    0.08
    achs
    0.08
    ä¸į足
    0.08
    Activations Density 0.018%

    No Known Activations