© 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. 55657
    Prev
    Next
    INDEX
    Explanations

    you can guess

    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
    baugh
    -0.09
     Narrow
    -0.09
    éĶ¼
    -0.09
    覺
    -0.08
    饬
    -0.08
    éİ
    -0.08
    èIJ½
    -0.08
    箧
    -0.08
    _definitions
    -0.08
    го
    -0.08
    POSITIVE LOGITS
    æijĨ
    0.09
    ici
    0.09
     already
    0.09
    å·²çĦ¶
    0.08
    å¿ı
    0.08
    ä»Ĭ天çļĦ
    0.08
    æ·±åĪĩ
    0.08
    @author
    0.08
    ä»ĸå·²ç»ı
    0.08
     Authors
    0.08
    Activations Density 0.020%

    No Known Activations