© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51352
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and scientific terms

    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
    /trans
    -0.06
    -
    -0.05
     ANSI
    -0.05
    °
    -0.05
     LG
    -0.05
    (
    -0.05
    (s
    -0.05
    /B
    -0.05
     MPC
    -0.04
     é
    -0.04
    POSITIVE LOGITS
    íĹĢ
    0.21
    ãĤ¤ãĥ³ãĤ¿ãĥ¼ãĥį
    0.20
    ãģ¨ãģ«ãģĭ
    0.20
    ê¹Ł
    0.20
    ãģĦãĤīãģ£
    0.20
    ëĸĪ
    0.19
    ãĮ¢
    0.19
    ãĤ¢ãĤ¤ãĥĨ
    0.19
    ãĤ¿ãĤ¤ãĥŁ
    0.19
    ãĤ¢ãĥ¡ãĥª
    0.19
    Activations Density 5.630%

    No Known Activations