© 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. 49304
    Prev
    Next
    INDEX
    Explanations

    stepping foot

    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
    她们
    -0.11
    ä¹ĸ
    -0.10
    æĿ¥æī¾
    -0.09
    æ¼Ķ
    -0.09
     lean
    -0.08
    achu
    -0.08
    .semantic
    -0.08
    æľ«ç«¯
    -0.08
    ä¿Ŀåį«
    -0.08
    åĥļ
    -0.08
    POSITIVE LOGITS
    è¸ı
    0.16
    èĦļ
    0.15
    èħ³
    0.14
     ног
    0.13
    è¸ıåħ¥
    0.13
     foot
    0.13
    è¿Ī
    0.12
    foot
    0.12
    ä¸ĢèĦļ
    0.12
     footing
    0.12
    Activations Density 0.049%

    No Known Activations