© 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. 48603
    Prev
    Next
    INDEX
    Explanations

    being or are followed by punctuation

    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
    äºĴ缸
    -0.09
    ItemImage
    -0.09
    为å¥ijæľº
    -0.08
    Bookmark
    -0.08
    èĢģåħµ
    -0.08
    æĸ°é²ľ
    -0.08
    éĻIJæŶ
    -0.08
    寸
    -0.08
    åıijçĶŁåľ¨
    -0.08
    olen
    -0.08
    POSITIVE LOGITS
    æĺ¯ä¸ĢåIJį
    0.10
    æĪijä¸įæĺ¯
    0.10
    身份
    0.10
    åħ·å¤ĩ
    0.09
    çļĦ身份
    0.09
    æŁIJç§įç¨ĭ度
    0.09
    çĴľ
    0.09
    她æĺ¯
    0.09
    åŀĭåı·
    0.09
    æĸĽ
    0.08
    Activations Density 0.094%

    No Known Activations