© 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. 18098
    Prev
    Next
    INDEX
    Explanations

    breakwater, sea erosion, graduate of, separation and

    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
    éĻį
    -0.09
    æĶĢ
    -0.09
    ä¹ĺ车
    -0.09
    -stock
    -0.09
    ä¼ļ计å¸Ī
    -0.09
     Hew
    -0.09
    纳ç¨İ
    -0.09
    çķľ
    -0.09
    ãĥķãĤ
    -0.09
     беÑģп
    -0.09
    POSITIVE LOGITS
    tail
    0.10
     tail
    0.09
     Tail
    0.09
    æĮ¡
    0.09
    ittel
    0.09
    åIJ¾
    0.08
    è£Ķ
    0.08
    æĦıä¹īä¸Ĭ
    0.08
     доÑģÑĤ
    0.08
    å¤ĸ
    0.08
    Activations Density 0.072%

    No Known Activations