© 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. 32509
    Prev
    Next
    INDEX
    Explanations

    pagination helper

    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
    ç¯Ĩ
    -0.11
    æ²¹æ¼Ĩ
    -0.08
    vid
    -0.08
    社ä¼ļ稳å®ļ
    -0.08
    è°¢éĤĢ
    -0.08
    ä¸ĢåIJį
    -0.08
    ught
    -0.07
    è±ģ
    -0.07
    ä¸Ģ款
    -0.07
    æľįåĬ¡æ°´å¹³
    -0.07
    POSITIVE LOGITS
    âĸ¸
    0.09
    è¶Ł
    0.09
     Hou
    0.09
    å¤ļä½Ļ
    0.09
    çĽĨ
    0.09
    éłĨ
    0.09
    鸿
    0.08
    adle
    0.08
     Olympia
    0.08
    .Keyword
    0.08
    Activations Density 0.049%

    No Known Activations