© 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. 22738
    Prev
    Next
    INDEX
    Explanations

    proto, prototype, protuberance, proto-oncogene

    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
    ses
    -0.09
    ç¬ij声
    -0.09
    空åīį
    -0.09
    åIJĮåŁİ
    -0.08
    ilian
    -0.08
    åĬ«
    -0.08
    adge
    -0.08
    OUS
    -0.08
    idar
    -0.08
    åıī
    -0.08
    POSITIVE LOGITS
    otypical
    0.11
    ocols
    0.11
    èĬ½
    0.09
    /proto
    0.09
    ting
    0.08
    å³Ļ
    0.08
    roys
    0.08
    ä¸ķ
    0.08
    (proto
    0.08
    奢ä¾Īåĵģ
    0.08
    Activations Density 0.056%

    No Known Activations