© 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. 63328
    Prev
    Next
    INDEX
    Explanations

    however,

    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
    æ£ł
    -0.13
     giác
    -0.11
    æŀľçĦ¶
    -0.11
    è¿ĩåIJİ
    -0.10
    ç¥Ŀè´º
    -0.10
    ester
    -0.09
    äºĨèµ·æĿ¥
    -0.09
    rollo
    -0.09
    å¦Ĥæŀľä¸įæĺ¯
    -0.09
    çĵ
    -0.08
    POSITIVE LOGITS
    uh
    0.09
    że
    0.09
    æĺ¯ä¸Ģ座
    0.09
    nuts
    0.08
    oldt
    0.08
    ä¸ĢèĦļ
    0.08
    æĺ¯ä¸ª
    0.08
    acos
    0.08
    æĺ¯ä¸Ģ项
    0.08
    AIM
    0.08
    Activations Density 0.035%

    No Known Activations