© 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. 30382
    Prev
    Next
    INDEX
    Explanations

    just because

    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
    hợ
    -0.09
    -ser
    -0.09
    æľīæĿ¡ä»¶çļĦ
    -0.09
    æľīæĿ¡ä»¶
    -0.09
    ÅĦ
    -0.08
    åĬłå·¥åİĤ
    -0.08
    erd
    -0.08
    ÐŁÐµÑĤ
    -0.08
    aed
    -0.08
     INTERRU
    -0.08
    POSITIVE LOGITS
    ä¸ĢæŶ
    0.12
    çľĭä¼¼
    0.10
    æŁIJ个
    0.10
    å°±èĥ½å¤Ł
    0.10
    è¾Ľèĭ¦
    0.10
    å°±è§īå¾Ĺ
    0.10
    æŁIJäºĽ
    0.10
    è¿Ļä¹Ī说
    0.09
    å¼ĢäºĨ
    0.09
    è¿Ļæł·åģļ
    0.09
    Activations Density 0.075%

    No Known Activations