© 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. 32109
    Prev
    Next
    INDEX
    Explanations

    poetry, poems, and poets

    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´§å¼ł
    -0.09
    æijĨ
    -0.09
    éŁ³
    -0.09
    åį§
    -0.09
    åıĮéĩį
    -0.09
    stin
    -0.09
    æ©Ľ
    -0.08
    ÑĤин
    -0.08
    äs
    -0.08
    èĢĹ
    -0.08
    POSITIVE LOGITS
    è¯Ĺè¯į
    0.22
    è¯ĹæŃĮ
    0.22
    ä¸Ģé¦ĸ
    0.20
     poetry
    0.19
    è¯Ĺ
    0.18
    è¯Ĺåı¥
    0.17
     poems
    0.17
     poem
    0.17
    è©©
    0.16
    æŃĮæĽ²
    0.15
    Activations Density 0.076%

    No Known Activations