© 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. 1991
    Prev
    Next
    INDEX
    Explanations

    films, historical events, or medical conditions

    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
    çľ¼ä¸ĭ
    -0.11
     laser
    -0.10
    æ¿Ģåħī
    -0.10
     Laser
    -0.09
    è°ª
    -0.09
    ä¼łçľŁ
    -0.09
    ãĥĬãĥ«
    -0.09
    æľĶ
    -0.09
    çĶµåŃIJéĤ®ä»¶
    -0.09
    å±Ĥ次
    -0.09
    POSITIVE LOGITS
    æ°ijåĽ½
    0.15
     telegram
    0.12
    æĬĹæĹ¥
    0.12
    æĬĹæĪĺ
    0.11
     Bolshevik
    0.11
    è¿ij代
    0.10
    天èĬ±
    0.10
    å½ĵæŶçļĦ
    0.10
    telegram
    0.09
     YM
    0.09
    Activations Density 1.627%

    No Known Activations