© 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. 18069
    Prev
    Next
    INDEX
    Explanations

    arguments or argument

    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»Ģä¹Īä¸ľè¥¿
    -0.09
    æĻ®
    -0.08
    è¹
    -0.08
    æĹłæīĢè°ĵ
    -0.08
    éļ¾æĢª
    -0.08
     dial
    -0.08
    ä¸Ģäºĭ
    -0.08
    åį¬
    -0.08
     Outlook
    -0.08
    amt
    -0.08
    POSITIVE LOGITS
    arguments
    0.15
     arguments
    0.15
     argument
    0.14
     Arguments
    0.13
    论è¯ģ
    0.13
    Argument
    0.12
    argument
    0.12
     Argument
    0.11
    辩æĬ¤
    0.11
    æı´
    0.10
    Activations Density 0.088%

    No Known Activations