© 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. 62795
    Prev
    Next
    INDEX
    Explanations

    teaching and presenting 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
    edar
    -0.10
    è¹ī
    -0.09
     اÙĦصØŃ
    -0.09
    ÑĨев
    -0.08
    htable
    -0.08
    ä¸Ģè¾ĪåŃIJ
    -0.08
    æĵ¦
    -0.08
    ãĥĵãĥ«
    -0.08
    被çĽĹ
    -0.08
    heim
    -0.08
    POSITIVE LOGITS
    讲座
    0.14
    讲课
    0.13
    宣讲
    0.13
    æİĪ课
    0.13
    讲
    0.13
    讲å¸Ī
    0.12
    æī§æķĻ
    0.11
    è¬Ľ
    0.11
    æĻ®åıĬ
    0.11
    LECT
    0.10
    Activations Density 0.094%

    No Known Activations