© 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. 1360
    Prev
    Next
    INDEX
    Explanations

    items following certain words

    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
    æľĢç¾İçļĦ
    -0.10
    æľĢå¤ļçļĦ
    -0.09
    ë²
    -0.09
     TORT
    -0.09
    æIJŃ
    -0.09
    elier
    -0.09
    ä¸įåIJĮçļĦ
    -0.09
    éĥ½æľīçĿĢ
    -0.09
    æ¯Ķè¾ĥç®Ģåįķ
    -0.09
    æľ´å®ŀ
    -0.09
    POSITIVE LOGITS
    ä¹Łä¸įè¦ģ
    0.10
    ä¸ĢæŶ
    0.10
    æĪĸ
    0.10
    ä¹ĭç±»
    0.09
    æĪĸåħ¶ä»ĸ
    0.08
    ades
    0.08
    ãĤĦ
    0.08
    æľªç»ı
    0.08
    çŃīå½¢å¼ı
    0.08
     or
    0.08
    Activations Density 0.134%

    No Known Activations