© 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. 58986
    Prev
    Next
    INDEX
    Explanations

    demanding improved services

    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
    æİĩ
    -0.09
    ovel
    -0.08
    å¯Ł
    -0.08
    à¸ķรà¸ĩ
    -0.08
    æĭĦ
    -0.08
    [email
    -0.08
    ä¼ļç»Ļ
    -0.08
    åħĥå®Ŀ
    -0.08
    _round
    -0.07
    彧
    -0.07
    POSITIVE LOGITS
    æĪĸ许æĺ¯
    0.09
    ä¹Łè®¸æĺ¯
    0.09
    èĭ¦
    0.09
    çļĦåİĭåĬĽ
    0.09
    ä¸ĢçĤ¹åĦ¿
    0.09
    çIJĨæĥ³ä¿¡å¿µ
    0.09
     lic
    0.09
    æģŃ
    0.09
    å©Ĩ
    0.09
    åİĭåĬĽ
    0.09
    Activations Density 0.145%

    No Known Activations