© 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. 61793
    Prev
    Next
    INDEX
    Explanations

    most popular

    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
    Apollo
    -0.09
    æį¢æĿ¥
    -0.09
    .crt
    -0.09
    çĮĹ
    -0.09
    å§ĭ建
    -0.08
     ÑģоÑģÑĤ
    -0.08
    æľĢ大çļĦ
    -0.08
    ä¸ĵéĹ¨ä¸º
    -0.08
    æľŁ
    -0.08
    ìĺ
    -0.08
    POSITIVE LOGITS
    ฯ
    0.09
    afa
    0.09
    ials
    0.08
     radiant
    0.08
    äºĭå®ľ
    0.08
    åĥļ
    0.08
     wax
    0.08
    称ä¹ĭ
    0.08
    icans
    0.08
    çĹĽ
    0.08
    Activations Density 0.030%

    No Known Activations