© 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. 2529
    Prev
    Next
    INDEX
    Explanations

    poet, poem, writer

    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
    éĺª
    -0.09
    ?url
    -0.09
    çĸ¤
    -0.09
    屯
    -0.09
     tvb
    -0.09
    æĮº
    -0.09
    å±ĢéĿ¢
    -0.09
    EDIA
    -0.08
    ç´§å¼ł
    -0.08
    å½±ä¸ļ
    -0.08
    POSITIVE LOGITS
    è¯Ĺ人
    0.21
    è¯ĹæŃĮ
    0.21
     poem
    0.18
    è¯Ĺ
    0.17
    è¯Ĺåı¥
    0.17
     poems
    0.16
    è©©
    0.16
    è¿Ļé¦ĸ
    0.15
     poets
    0.15
     poet
    0.15
    Activations Density 0.189%

    No Known Activations