© 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. 18012
    Prev
    Next
    INDEX
    Explanations

    points, touchdowns, runs, hits, goals

    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
    æ¯ıå¹´
    -0.10
    éĢIJå¹´
    -0.09
    æ¯ıæľĪ
    -0.09
    åħ¨åĽ½
    -0.09
    çĶ·
    -0.08
    æĥ°
    -0.08
    å¹³åĿĩæ°´å¹³
    -0.08
    ucking
    -0.08
    åİĨå¹´
    -0.08
    é½IJ
    -0.08
    POSITIVE LOGITS
    åħ¨æĹ¥
    0.11
    åħ¨è¿ĩç¨ĭ
    0.10
    ä¸Ģ个å°ıæŶ
    0.10
    蹿
    0.09
    æľ¬è½®
    0.09
    个å°ıæŶ
    0.09
    è¢Ĥ
    0.09
    inous
    0.09
    èĥ¸åīį
    0.09
    æĭĽåij¼
    0.09
    Activations Density 0.032%

    No Known Activations