© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37000
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
    ä¸įåºĶ
    -0.10
    并ä¸İ
    -0.09
    èĻ½çĦ¶
    -0.09
    ä¸į该
    -0.09
    èĻ½
    -0.09
    åį´æ²¡æľī
    -0.09
    ä¸įåºĶ该
    -0.08
    éªŀ
    -0.08
     пÑĢиÑĩ
    -0.08
    ä¸įåĩĨ
    -0.08
    POSITIVE LOGITS
    èĢĮæĺ¯
    0.28
     sondern
    0.17
    ä¹Łä¸įåı¯èĥ½
    0.11
    å¾Ģå¾Ģæĺ¯
    0.10
    éĤ£æĺ¯
    0.10
    åįķ纯
    0.10
    ä¹Łä¸įæĺ¯
    0.09
    éĤ£ä¹Īç®Ģåįķ
    0.09
    æģ°æģ°
    0.09
    æľĶ
    0.09
    Activations Density 0.075%

    No Known Activations