© 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. 54008
    Prev
    Next
    INDEX
    Explanations

    set of

    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
    澡
    -0.10
    太å¤ļçļĦ
    -0.09
     constitution
    -0.09
    ä¸İåIJ¦
    -0.08
    ä¸ĢæĿ¡
    -0.08
    天空
    -0.08
    ä¸Ģæľ¬ä¹¦
    -0.08
    èµ·çłģ
    -0.07
    室
    -0.07
    éĻĶ
    -0.07
    POSITIVE LOGITS
    ves
    0.11
     goodies
    0.10
    举æݪ
    0.09
    mah
    0.09
    ÙħØ·ÙĦ
    0.09
    rens
    0.09
     веÑī
    0.09
    ÙħصÙĦ
    0.08
     laps
    0.08
    äºĭæĥħ
    0.08
    Activations Density 0.124%

    No Known Activations