© 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. 23493
    Prev
    Next
    INDEX
    Explanations

    academic and scientific fields

    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
    arring
    -0.09
    褶
    -0.09
    åĪ«
    -0.09
    aben
    -0.08
    çļĦæĸĩåĮĸ
    -0.08
    æĢ§çļĦ
    -0.08
    è¯Ħå§Ķ
    -0.08
    urally
    -0.08
    iot
    -0.08
    hiba
    -0.08
    POSITIVE LOGITS
    ä¸ĢåĽŀäºĭ
    0.09
    &_
    0.09
    èĭ´
    0.08
     electr
    0.08
    çľĭä»ĸ
    0.08
    åĽłä¸ºæĪij
    0.08
    å¿ĥçIJĨåѦ
    0.08
    _statistics
    0.08
     medicine
    0.08
     theory
    0.08
    Activations Density 0.219%

    No Known Activations