© 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. 38912
    Prev
    Next
    INDEX
    Explanations

    written or arranged in text or images

    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
    åłµ
    -0.10
    æĹłæĥħ
    -0.10
    .setInput
    -0.10
    PCS
    -0.09
    éģł
    -0.09
    褴
    -0.09
    medi
    -0.09
    天èĬ±æĿ¿
    -0.09
    å¬ĸ
    -0.09
    身å¿ĥ
    -0.09
    POSITIVE LOGITS
    ç¯Ĩ
    0.11
    åĽ¾æ¡Ī
    0.10
    åŃĹæł·
    0.10
    åį°ç«ł
    0.10
    éķĤ
    0.09
     ink
    0.09
    çļĦæĸĩåŃĹ
    0.09
    åĪ»
    0.09
    ink
    0.09
    åį°åĪ·
    0.09
    Activations Density 0.096%

    No Known Activations