© 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. 31195
    Prev
    Next
    INDEX
    Explanations

    preparing for future

    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¸įåģľ
    -0.10
    æ´»çĿĢ
    -0.10
    åħ´æĹº
    -0.09
    å·¡
    -0.09
    ç²ī
    -0.09
    太空
    -0.08
    æĶ¯éĺŁ
    -0.08
    ç´§æĢ¥
    -0.08
    setId
    -0.08
     SLOT
    -0.08
    POSITIVE LOGITS
    åĩĨå¤ĩ
    0.13
    å¿įåıĹ
    0.13
    åĩĨå¤ĩ好
    0.13
    å¿ĥçIJĨ
    0.11
    æī¿åıĹ
    0.11
     brace
    0.10
    åģļ好
    0.10
    é¢ĦæĸĻ
    0.10
    è¿İæİ¥
    0.10
    æºĸåĤĻ
    0.10
    Activations Density 0.031%

    No Known Activations