© 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. 62113
    Prev
    Next
    INDEX
    Explanations

    any followed by a noun

    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
    ä¸įçŁ¥ä¸įè§ī
    -0.11
    ãģŀ
    -0.09
    大声
    -0.09
    ç¥ĸçĪ¶
    -0.09
    ä¸įçŁ¥ä¸į
    -0.09
    çļĦçĭ¬çī¹
    -0.09
    æĽ´éĩįè¦ģçļĦ
    -0.08
    éĹº
    -0.08
    /from
    -0.08
    -build
    -0.08
    POSITIVE LOGITS
    人éĥ½
    0.10
    orno
    0.10
    çļĦ人éĥ½
    0.09
    beit
    0.09
    èĭ¥æľī
    0.09
    çģ¼
    0.09
    ERVE
    0.09
    仿
    0.09
    ern
    0.08
    éģĩåĪ°
    0.08
    Activations Density 0.020%

    No Known Activations