© 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. 63442
    Prev
    Next
    INDEX
    Explanations

    rain, storm, flooding, disaster, nuclear medicine

    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
    æįŁ
    -0.10
    ç¾Ĭæ¯Ľ
    -0.09
    èĢĺ
    -0.09
    äºĶæĺŁ
    -0.09
     initials
    -0.09
    RAL
    -0.09
    èĭ¥æľī
    -0.09
    çĴŀ
    -0.08
    ç¯Ļ
    -0.08
    .mi
    -0.08
    POSITIVE LOGITS
    æ»ŀ
    0.11
    éĽ¨æ°´
    0.11
    æļ´éĽ¨
    0.10
    å¡Į
    0.10
    å¤§éĽ¨
    0.10
    æ»Ĥ
    0.10
    æ¶Ŀ
    0.09
    ä¸Ģåľº
    0.09
    æ½į
    0.09
    åĢĴéľī
    0.09
    Activations Density 0.055%

    No Known Activations