© 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. 19324
    Prev
    Next
    INDEX
    Explanations

    short and shortcode

    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
    å·¢
    -0.10
    /generated
    -0.10
    elts
    -0.09
    æģ©æĸ½
    -0.09
    ло
    -0.09
    æį§
    -0.09
    icing
    -0.08
    è¡ĮåĬ¨è®¡åĪĴ
    -0.08
    足
    -0.08
    ees
    -0.08
    POSITIVE LOGITS
    ÑĢад
    0.09
    ridge
    0.09
    寥
    0.09
    åºľ
    0.08
    ych
    0.08
    ighted
    0.08
    è¡¿
    0.08
    uttle
    0.08
    è¤Ĥ
    0.08
    нÑĥ
    0.08
    Activations Density 0.003%

    No Known Activations