© 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. 48329
    Prev
    Next
    INDEX
    Explanations

    swirling circular motion

    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
    rts
    -0.10
    ãģ¹ãģį
    -0.09
    æľīçļĦ人
    -0.09
     behalf
    -0.09
    åIJĥå¾Ĺ
    -0.08
     bloc
    -0.08
    opus
    -0.08
    ych
    -0.08
    à¸Īà¸ļ
    -0.08
    ement
    -0.08
    POSITIVE LOGITS
    ingly
    0.13
    åĽ½ç±į
    0.11
    wind
    0.11
    æ½Ń
    0.10
    blade
    0.10
    åħ¨èĥ½
    0.10
    笳
    0.10
    èģĴ
    0.09
    fully
    0.09
    èĪ¬çļĦ
    0.09
    Activations Density 0.006%

    No Known Activations