© 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. 49444
    Prev
    Next
    INDEX
    Explanations

    car and motorcycle manufacturers

    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
     Von
    -0.10
    REN
    -0.10
    ä¸ŃåĽ½èģĶéĢļ
    -0.09
    çķĮçļĦ
    -0.09
    ren
    -0.09
    è¡Ķ
    -0.09
    åıįæĺłåĩº
    -0.09
    綦
    -0.09
    è¿Ļå¼ł
    -0.08
    ifa
    -0.08
    POSITIVE LOGITS
    tight
    0.09
    pent
    0.08
    åĭ¤
    0.08
     sadd
    0.08
    æİĴæĶ¾
    0.08
    ศา
    0.08
    æijĦ
    0.08
    åħ¬åı¸å°Ĩ
    0.08
     handmade
    0.08
    æİĴæ¯Ĵ
    0.08
    Activations Density 0.049%

    No Known Activations