© 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. 21339
    Prev
    Next
    INDEX
    Explanations

    species names taxonomic classification

    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
     займ
    -0.09
    ÑĮе
    -0.08
    åħįç¨İ
    -0.08
    æĿłæĿĨ
    -0.08
    AREN
    -0.08
    èįª
    -0.08
    лев
    -0.08
     далÑĮ
    -0.08
    Vien
    -0.08
     trick
    -0.08
    POSITIVE LOGITS
    çķ¸
    0.10
     thoát
    0.10
    åĮħ裹
    0.09
    åĮħ
    0.09
    <!--[
    0.09
    åºķä¸ĭ
    0.09
    trys
    0.09
     opin
    0.08
    моÑĢ
    0.08
     Emin
    0.08
    Activations Density 0.257%

    No Known Activations