© 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. 39946
    Prev
    Next
    INDEX
    Explanations

    speaker and keynote talks

    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
    å¯Ŀ
    -0.10
    åħ¬çº¦
    -0.09
    让å®ĥ
    -0.09
    åĢĮ
    -0.09
    ç¼´è´¹
    -0.09
    /art
    -0.08
    åįĴ
    -0.08
    å°ıçĻ½
    -0.08
    bara
    -0.08
    çĦ¶
    -0.08
    POSITIVE LOGITS
    æ¼Ķ讲
    0.15
    讲å¸Ī
    0.15
    讲座
    0.15
    宣讲
    0.13
    讲课
    0.13
     lecture
    0.12
    åºĶéĤĢ
    0.11
     lect
    0.11
    æİĪ课
    0.11
     speaker
    0.11
    Activations Density 0.127%

    No Known Activations