© 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. 35591
    Prev
    Next
    INDEX
    Explanations

    Fight Club meets

    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
    åªĴ
    -0.10
    èĭ¥æľī
    -0.09
    bucks
    -0.09
     Ñģобой
    -0.09
    -BEGIN
    -0.09
    èİĵ
    -0.09
    iami
    -0.09
    InView
    -0.09
    Sexy
    -0.09
     Holl
    -0.09
    POSITIVE LOGITS
    åħ¢
    0.08
    èģĮä¸ļçĶŁæ¶¯
    0.08
    ct
    0.08
    潮湿
    0.08
    æīij
    0.08
    湿润
    0.08
    ÑĢин
    0.08
    æĤ²ä¼¤
    0.08
    ennon
    0.08
     powers
    0.08
    Activations Density 0.002%

    No Known Activations