© 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. 19051
    Prev
    Next
    INDEX
    Explanations

    not want

    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
    ä¹ŁæĽ¾
    -0.10
    åĩłä¹İæīĢæľī
    -0.10
    ä¸įåIJĮç¨ĭ度
    -0.09
    çľĭä¸Ģçľĭ
    -0.09
    å¾Īå¤ļäºĭæĥħ
    -0.09
    noinspection
    -0.09
    å¾Īå¤ļ人éĥ½
    -0.09
    çļĦä¸ĢäºĽ
    -0.09
    æ¥ł
    -0.09
    çıłæ±Ł
    -0.09
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.16
     anymore
    0.16
    ä»»ä½ķå½¢å¼ı
    0.14
    ä»»ä½ķ
    0.12
     anything
    0.12
    æľīè¿Ļæł·çļĦ
    0.12
     nor
    0.12
    ä¹Łä¸įèĥ½
    0.12
    ä»»ä½ķä¸Ģ个
    0.11
    ä»»ä½ķ人
    0.11
    Activations Density 0.085%

    No Known Activations