© 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. 56449
    Prev
    Next
    INDEX
    Explanations

    wine or wines

    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
    èĤļåŃIJ
    -0.12
    æĸĭ
    -0.09
    æĻĤ代
    -0.09
    åģ¥åº·ç®¡çIJĨ
    -0.09
    ä¸įåIJĪçIJĨ
    -0.09
    羸
    -0.09
    çľĭä¸įåĪ°
    -0.09
    æĸ¹æīį
    -0.08
    çľĭçĶµå½±
    -0.08
    ahr
    -0.08
    POSITIVE LOGITS
    èij¡èIJĦéħĴ
    0.13
     wines
    0.11
     wine
    0.10
    éħ¿éĢł
    0.10
    ä¸Ģ款
    0.09
    æľªç»ı
    0.09
    移æ°ij
    0.09
    æ½ĩ
    0.09
     иÑģп
    0.09
    骨干
    0.09
    Activations Density 0.075%

    No Known Activations