© 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. 30461
    Prev
    Next
    INDEX
    Explanations

    coaching and teaching roles

    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
    请大家
    -0.09
    åĺĺ
    -0.09
    æħ°
    -0.09
    å°ıä¼Ļ伴们
    -0.09
    å°ıä¼Ļä¼´
    -0.08
    ä¸įä½³
    -0.08
    çļĦåIJĪä½ľ
    -0.08
    æīŃ
    -0.08
    æĮ«
    -0.08
    绥
    -0.08
    POSITIVE LOGITS
    æķĻåѦ
    0.13
     teaching
    0.11
    æķĻãģĪ
    0.11
    æķĻåѸ
    0.11
     Teach
    0.10
    æī§æķĻ
    0.10
    å¼Ĥåľ°
    0.10
    arsity
    0.09
    æķĻçłĶ
    0.09
     teaches
    0.09
    Activations Density 0.102%

    No Known Activations