© 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. 11760
    Prev
    Next
    INDEX
    Explanations

    mini- prefix

    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
    æŁ¥çľĭæĽ´å¤ļ
    -0.10
    banks
    -0.09
    çļĦ对象
    -0.09
    stras
    -0.09
    èĩ³ä¸Ĭ
    -0.08
    Ui
    -0.08
    岸
    -0.08
    /vendor
    -0.08
    sel
    -0.08
     Reich
    -0.08
    POSITIVE LOGITS
    mini
    0.12
     mini
    0.11
    ãĥŁãĥĭ
    0.11
    ature
    0.10
    Mini
    0.10
    æѤç§į
    0.10
    atures
    0.10
    -mini
    0.10
    åĽ½åĬ¡
    0.10
    IMUM
    0.09
    Activations Density 0.178%

    No Known Activations