© 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. 54340
    Prev
    Next
    INDEX
    Explanations

    biological and medical terms

    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
    itsu
    -0.10
    ancock
    -0.10
    /mat
    -0.10
    æĺ¶
    -0.10
    cord
    -0.09
    éļıæŶéļı
    -0.09
    indle
    -0.09
    .mat
    -0.09
    vasion
    -0.09
    ä¹ĸ
    -0.09
    POSITIVE LOGITS
     called
    0.12
    åı«åģļ
    0.12
    åı«
    0.11
    åIJįåı«
    0.11
    被称为
    0.10
    -called
    0.10
    对åħ¬åı¸
    0.09
    called
    0.09
    称为
    0.09
    far
    0.09
    Activations Density 0.245%

    No Known Activations