© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9740
    Prev
    Next
    INDEX
    Explanations

    wood and Clarkson

    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
    çĪ·
    -0.10
    亲
    -0.10
    åħīåѦ
    -0.09
    è¿¢
    -0.09
    é»ı
    -0.09
    ule
    -0.09
    åı¯æݧ
    -0.08
     Isles
    -0.08
    linkplain
    -0.08
    æĭĽæĶ¶
    -0.08
    POSITIVE LOGITS
    æĸ¯
    0.10
    è¾ĩ
    0.09
    çļĩåĨł
    0.09
    èĻ¹
    0.09
    æ´ĹèĦ¸
    0.08
    ç£ħ
    0.08
    èĬĤèĥ½çݯä¿Ŀ
    0.08
     Fixes
    0.08
     Colbert
    0.08
    yas
    0.08
    Activations Density 0.001%

    No Known Activations