© 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. 27528
    Prev
    Next
    INDEX
    Explanations

    what are the

    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
    该项
    -0.09
    ä¸ĢåIJį
    -0.09
    ä¸įæĺ¯ä¸Ģ个
    -0.09
    ä¸Ģè§Ĵ
    -0.09
     Chand
    -0.08
    åĥı个
    -0.08
    æł¼å°Ķ
    -0.08
     itself
    -0.08
    esco
    -0.08
    åħ¨éĿ¢
    -0.08
    POSITIVE LOGITS
    两大
    0.09
    @js
    0.09
    åĵªäºĽ
    0.09
    DUCT
    0.09
    enz
    0.09
    æ´Ļ
    0.09
    aled
    0.08
    éĵµ
    0.08
    orte
    0.08
    èĿ®
    0.08
    Activations Density 0.071%

    No Known Activations