© 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. 54529
    Prev
    Next
    INDEX
    Explanations

    either or

    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
    ãģ¨
    -0.08
    mage
    -0.07
    çıħ
    -0.07
    ä¸įåĪ°
    -0.07
    went
    -0.07
    ANDLE
    -0.07
    ä¸ĢåĪĩ
    -0.07
     Matters
    -0.07
    è±ģ
    -0.07
    /of
    -0.07
    POSITIVE LOGITS
    æĪĸæĺ¯
    0.36
     or
    0.33
    æĪĸèĢħ
    0.31
    æĪĸèĢħæĺ¯
    0.31
    æĪĸåħ¶ä»ĸ
    0.30
    æĪĸèĢħåħ¶ä»ĸ
    0.29
     или
    0.28
    æĪĸ
    0.28
     hoặc
    0.26
     æĪĸ
    0.26
    Activations Density 0.481%

    No Known Activations