© 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. 17836
    Prev
    Next
    INDEX
    Explanations

    passing, passed, or pass words

    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
    cing
    -0.11
    æī¼
    -0.10
    壬
    -0.10
    ç²Ĺ
    -0.09
    ä¸ĢæŃ¥æŃ¥
    -0.09
    nik
    -0.09
    æŀģ端
    -0.09
    hop
    -0.09
    è´¯éĢļ
    -0.09
    æĹłå¿§
    -0.09
    POSITIVE LOGITS
    ç´¯
    0.10
     Thom
    0.10
    DOT
    0.09
    çļĦç²¾ç¥ŀ
    0.09
    asar
    0.09
    åħīèį£
    0.09
    apg
    0.09
    çļĦæĢĿæĥ³
    0.08
    vara
    0.08
    俳
    0.08
    Activations Density 0.012%

    No Known Activations