© 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. 11279
    Prev
    Next
    INDEX
    Explanations

    not followed by comma

    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
     EO
    -0.08
    elda
    -0.08
     thus
    -0.08
    è°ĥçIJĨ
    -0.08
    rama
    -0.08
    çı¥
    -0.08
    æľīèĥ½åĬĽ
    -0.07
     BAM
    -0.07
    æĸĭ
    -0.07
    ä»Ģä¹Īæł·
    -0.07
    POSITIVE LOGITS
    åĪ©äºļ
    0.11
    lé
    0.10
    ÑģÑĤеÑĢ
    0.09
    hợ
    0.09
    LIBINT
    0.09
    compiled
    0.09
     Grove
    0.09
    ä¸ĩéĩĮ
    0.08
    请æĤ¨
    0.08
    精彩
    0.08
    Activations Density 0.028%

    No Known Activations