© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36685
    Prev
    Next
    INDEX
    Explanations

    actions and sensory experiences

    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
     mic
    -0.09
    mic
    -0.09
    راس
    -0.09
    iar
    -0.09
    æĹ¢æĺ¯
    -0.09
    assist
    -0.08
    grams
    -0.08
    éģĵå¾·
    -0.08
    gm
    -0.08
     Verde
    -0.08
    POSITIVE LOGITS
    æĸ¯åŁº
    0.11
    ç²¹
    0.10
    åĶ³
    0.10
    æĮĩåįĹ
    0.09
    ÑģÑĤолÑĮ
    0.09
    åIJĦç§įåIJĦæł·
    0.09
    å¸ĮæľĽå¤§å®¶
    0.09
    è§īå¾Ĺå¾Ī
    0.09
    aised
    0.09
    dummy
    0.09
    Activations Density 0.083%

    No Known Activations