© 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. 16983
    Prev
    Next
    INDEX
    Explanations

    Master of students should read

    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
    ill
    -0.10
    æļ¨
    -0.09
    ç½Ĥ
    -0.09
    ç§ĥ
    -0.09
    缸æ¯Ķ
    -0.09
    ange
    -0.09
    æĵİ
    -0.09
    atto
    -0.09
    å²Ĺ
    -0.08
    ất
    -0.08
    POSITIVE LOGITS
    ä»¥äººä¸ºæľ¬
    0.10
    宽éĺĶ
    0.09
    mour
    0.08
    çľ¼çķĮ
    0.08
    è·Łä¸įä¸Ĭ
    0.08
    à´´
    0.08
    ripp
    0.08
    isha
    0.08
    itzer
    0.08
     Chand
    0.08
    Activations Density 0.477%

    No Known Activations