© 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. 54973
    Prev
    Next
    INDEX
    Explanations

    really

    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
    赫
    -0.09
    ç«ŁçĦ¶
    -0.09
    éĵĥ
    -0.09
    monkey
    -0.09
     EVER
    -0.08
    å¢ĥ
    -0.08
    æĺ¾çĦ¶
    -0.08
    à¸ķà¸Ļ
    -0.08
    ennen
    -0.08
    çĦī
    -0.08
    POSITIVE LOGITS
    æĦıä¹īä¸ĬçļĦ
    0.11
     shorthand
    0.09
    ä»Ģä¹Īéĥ½
    0.09
    èĻ±
    0.09
    æĦıä¹īä¸Ĭ
    0.09
    ä¸įåľ¨ä¹İ
    0.09
    éªħ
    0.09
    åİ»çľĭçľĭ
    0.09
    å·®ä¸įå¤ļ
    0.09
    Buzz
    0.08
    Activations Density 0.028%

    No Known Activations