© 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. 38756
    Prev
    Next
    INDEX
    Explanations

    quotation marks, speech, or sayings

    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
    æĽ´å¤ļä¿¡æģ¯
    -0.11
    âĢ£
    -0.10
    åıĪæĺ¯
    -0.09
    èĩªç§°
    -0.09
    combe
    -0.09
    ä¹Łæľīä¸ĢäºĽ
    -0.09
    åıĪè¦ģ
    -0.08
    声
    -0.08
     elder
    -0.08
    ä¸įåıĬ
    -0.08
    POSITIVE LOGITS
    éĤ£å°±æĺ¯
    0.09
    泡
    0.09
    ewis
    0.09
    åŃIJåŃĻ
    0.08
    èĥ½è®©
    0.08
    ä¸įæĢķ
    0.08
    åħ¬ä¸»
    0.08
    è§ģè¯Ĩ
    0.08
    å·¥ä½ľæľºåĪ¶
    0.08
    mock
    0.08
    Activations Density 0.037%

    No Known Activations