© 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. 18563
    Prev
    Next
    INDEX
    Explanations

    special characters marking sections

    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
    ç»ĦæĪIJçļĦ
    -0.09
    çĬĬ
    -0.09
    åį¡è½¦
    -0.09
    åķĦ
    -0.09
    沸
    -0.09
    æľ¬æĿ¥å°±
    -0.09
    æ¡İ
    -0.09
    å³Ļ
    -0.08
    /link
    -0.08
    æķ´æķ´
    -0.08
    POSITIVE LOGITS
    ä½ĵä¼ļåĪ°
    0.09
    ä¹İ
    0.08
     Chill
    0.08
    timing
    0.08
    å¿ĥå¢ĥ
    0.08
    羣æŃ£åģļåĪ°
    0.08
    人æĸĩ
    0.08
    æĦŁè§īåĪ°
    0.08
    çIJĨ解
    0.08
    å£ķ
    0.08
    Activations Density 0.100%

    No Known Activations