© 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. 49759
    Prev
    Next
    INDEX
    Explanations

    more comparison

    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¸İåIJ¦
    -0.12
    ä¸įåĨį
    -0.10
    ãģĵãģĿ
    -0.10
    æĪĸåħ¶ä»ĸ
    -0.09
    åıĪ称
    -0.09
    знаком
    -0.09
    åIJĮæł·
    -0.09
    æĪĽ
    -0.09
    严éĩįå½±åĵį
    -0.09
    æĪĸèĢħåħ¶ä»ĸ
    -0.09
    POSITIVE LOGITS
    模èĮĥ
    0.09
    ä¸įçĦ¶
    0.09
    寸
    0.08
     tac
    0.08
    kwargs
    0.08
    缼ä¸ĸ
    0.08
    çīĪ
    0.08
    sembly
    0.08
    解æĶ¾
    0.08
     Shin
    0.07
    Activations Density 0.033%

    No Known Activations