© 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. 57685
    Prev
    Next
    INDEX
    Explanations

    court and legal documents

    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
    ÑĮÑı
    -0.09
    åıįä¹ĭ
    -0.09
    åı¦ä¸Ģ
    -0.09
    raq
    -0.08
    èģĥ
    -0.08
    éĻ
    -0.08
     another
    -0.08
    æ¯ķç«Łæĺ¯
    -0.08
    åı¦ä¸Ģä½į
    -0.08
    æľīéĴ±
    -0.08
    POSITIVE LOGITS
    æ¶ķ
    0.10
    éĤ°
    0.10
    åĬªåĬĽ
    0.09
    orny
    0.09
    ITOR
    0.09
    泪水
    0.09
    éķ¿ä¸īè§Ĵ
    0.09
    驽
    0.09
    cust
    0.08
     tán
    0.08
    Activations Density 0.018%

    No Known Activations