© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20351
    Prev
    Next
    INDEX
    Explanations

    contrasting outcomes or limitations

    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
    abelle
    -0.08
    æĪijå·²ç»ı
    -0.08
    转载请
    -0.07
    ounter
    -0.07
     Wrapped
    -0.07
     Over
    -0.07
     оÑģобенно
    -0.07
    ucher
    -0.07
    çķ¢ç«Ł
    -0.07
    pp
    -0.07
    POSITIVE LOGITS
    éļ¾æĢª
    0.12
     Colbert
    0.10
    çľĭä¼¼
    0.10
    æģ¯æģ¯
    0.10
    è¹ĭ
    0.10
    çĶ±æѤåı¯è§ģ
    0.10
    åĸ½
    0.10
    é¹Ń
    0.10
    å°±æľīäºĨ
    0.10
    åı¯è§ģ
    0.10
    Activations Density 0.131%

    No Known Activations