© 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. 28093
    Prev
    Next
    INDEX
    Explanations

    electric organ, turtling, skunks, release

    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
    ä¸įçĽ¸ä¿¡
    -0.11
    å´Ľ
    -0.09
    è§ģè¯ģ
    -0.09
    allel
    -0.09
    ãi
    -0.09
    æĪIJåIJį
    -0.09
     deser
    -0.08
    ITES
    -0.08
    åIJįä¹ī
    -0.08
    æķ´é¡¿
    -0.08
    POSITIVE LOGITS
    éķ¿èĢģ
    0.10
    鼷
    0.09
    ç«ĭåį³
    0.09
     пÑĢава
    0.09
    æĸĭ
    0.09
    ç»Ŀ对
    0.08
    å·«
    0.08
    icky
    0.08
    rames
    0.08
    ç«ł
    0.08
    Activations Density 0.084%

    No Known Activations