© 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. 11489
    Prev
    Next
    INDEX
    Explanations

    hover verbs and related words

    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
    sv
    -0.09
     Whip
    -0.09
    .Must
    -0.09
    bos
    -0.08
     bingo
    -0.08
    ToBounds
    -0.08
    AVA
    -0.08
    èįł
    -0.08
    orus
    -0.08
    blink
    -0.08
    POSITIVE LOGITS
    ingly
    0.11
    craft
    0.11
    å¾Ĺä½ı
    0.10
    åĩłå¼ł
    0.09
    éķ¿ä¸īè§Ĵ
    0.09
    алÑĮ
    0.09
    æĻ¯å¾·
    0.09
     hovered
    0.09
    åĩłåIJį
    0.09
     hovering
    0.08
    Activations Density 0.007%

    No Known Activations