© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38166
    Prev
    Next
    INDEX
    Explanations

    Asian Americans, film, financial, society, athletics

    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
    åĿŁ
    -0.10
    è¯ķçĤ¹å·¥ä½ľ
    -0.10
    è¹²
    -0.08
    ä»»æķĻ
    -0.08
    ETO
    -0.08
    èµ°åĩºæĿ¥
    -0.08
    ç®ĹäºĨ
    -0.08
    Israeli
    -0.08
    å¤§éĽ¨
    -0.07
     Fav
    -0.07
    POSITIVE LOGITS
    èĸ®
    0.09
    æĮł
    0.09
    eus
    0.09
    ç½ij讯
    0.09
    FOX
    0.09
    .INTER
    0.08
    æīĢè°ĵ
    0.08
    çĿ¦
    0.08
    æłª
    0.08
    .localized
    0.08
    Activations Density 0.039%

    No Known Activations