© 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. 20681
    Prev
    Next
    INDEX
    Explanations

    business roles: producer, maker, manufacturer

    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
    èĩªæĿ¥
    -0.08
    ä¸Ģ个人
    -0.08
    ä½łå°±
    -0.08
    éĨĴ
    -0.08
    åī¯ä¹¦è®°
    -0.08
    aled
    -0.08
    ilan
    -0.08
    æį¢ä¸ª
    -0.08
     involuntary
    -0.08
    าà¸ĩ
    -0.08
    POSITIVE LOGITS
    éĤ¸
    0.10
    ording
    0.10
    åħ¬è®¤çļĦ
    0.09
    ugh
    0.09
    åħ¬è®¤
    0.09
    lein
    0.08
    åĬ£
    0.08
    erin
    0.08
    ë£Į
    0.08
    ÑģÑĤво
    0.08
    Activations Density 0.062%

    No Known Activations