© 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. 62380
    Prev
    Next
    INDEX
    Explanations

    years, decades, since

    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
    åľ°éģĵ
    -0.10
    å¾Īå¿«
    -0.09
    ä¸ī个æľĪ
    -0.09
    æīĭåĬ¿
    -0.09
    æĶ»åħĭ
    -0.09
    两个æľĪ
    -0.08
    ìĦ±
    -0.08
    åIJĮå¹´
    -0.08
    å¯ĴåĨ¬
    -0.08
    å½ĵåľ°
    -0.08
    POSITIVE LOGITS
    åĩłåįģå¹´
    0.15
    ä¸Ĭä¸ĸ纪
    0.12
     decades
    0.12
    æĶ¹éĿ©å¼ĢæĶ¾
    0.11
    æĤ¨åIJĮæĦı
    0.11
    对ä¸įèµ·
    0.11
    é»ĺ认
    0.10
    åħ±è¯Ĩ
    0.10
    çĻ¾å¹´
    0.10
    åīįè¾Ī
    0.09
    Activations Density 0.105%

    No Known Activations