© 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. 5948
    Prev
    Next
    INDEX
    Explanations

    and/or

    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
    åįģéĩĮ
    -0.09
    åIJ±
    -0.09
    æķħ乡
    -0.09
    çļĦ人çĶŁ
    -0.09
    è¿Ļ家åħ¬åı¸
    -0.09
    çī¹æĸ¯
    -0.08
    tat
    -0.08
    ç¨ļ
    -0.08
    ç®Ĺ
    -0.08
    èĤŁ
    -0.08
    POSITIVE LOGITS
    ãĥ¡ãĥ¼ãĤ
    0.10
    çļĦç¡®
    0.09
    ä¸Ģå®ļ
    0.09
    æľīä¸Ģå®ļ
    0.09
    å¤ĩ
    0.09
    íĺģ
    0.09
     richest
    0.09
    ä¸įåIJĮç¨ĭ度
    0.08
    涨
    0.08
    è´«
    0.08
    Activations Density 0.171%

    No Known Activations