© 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. 56823
    Prev
    Next
    INDEX
    Explanations

    advertising and free experiences

    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
     poste
    -0.10
    æ´ĭæ´ĭ
    -0.09
    -half
    -0.08
    /entities
    -0.08
    ACS
    -0.08
     Strom
    -0.08
    Posting
    -0.08
    ath
    -0.08
    å½ĵ天
    -0.08
    èĬ
    -0.08
    POSITIVE LOGITS
    éļĻ
    0.09
    ç½ħ
    0.09
    ä¸įå¿į
    0.09
    èĨĺ
    0.09
    è°ķ
    0.09
    åŀ¢
    0.08
    ä¸įåı¯éģ¿åħį
    0.08
    è¢Ĥ
    0.08
    æ¸į
    0.08
    å»Ĭ
    0.08
    Activations Density 0.018%

    No Known Activations