© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8945
    Prev
    Next
    INDEX
    Explanations

    cups and sandwiches

    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
    该éĻ¢
    -0.09
    itto
    -0.09
     flatt
    -0.08
    èĨ»
    -0.08
    blank
    -0.08
    éĿ
    -0.08
    çĪµå£«
    -0.08
     blank
    -0.08
    anne
    -0.08
    è¯¥æł¡
    -0.07
    POSITIVE LOGITS
    åIJĦèĩª
    0.11
    ä½łè¯´
    0.10
    æĿ¯
    0.10
    кÑĥп
    0.09
    çݲ
    0.09
    URA
    0.09
    USTER
    0.09
    éĢīæĭ
    0.09
    unes
    0.09
    ijke
    0.09
    Activations Density 0.007%

    No Known Activations