© 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. 11715
    Prev
    Next
    INDEX
    Explanations

    game, form, application, record, system

    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
     позвол
    -0.10
    åıªè¦ģä½ł
    -0.09
    ä»Ģä¹Īåij¢
    -0.09
    çĦ¶æĺ¯
    -0.09
    éĥģ
    -0.08
    令
    -0.08
     proprietary
    -0.08
    让
    -0.08
    ä½Ĩä¸įéĻIJäºİ
    -0.08
     serialVersionUID
    -0.08
    POSITIVE LOGITS
    åıĺå¾ĹæĽ´åĬł
    0.11
    åıĺå¾Ĺ
    0.11
    åıĺå¾ĹæĽ´
    0.10
    éĵį
    0.10
    æķ´ä½ĵ
    0.10
    çļĦæķ´ä½ĵ
    0.09
     itself
    0.08
     overall
    0.08
    çļĦ羣å®ŀæĢ§
    0.08
    ä»Ĺ
    0.08
    Activations Density 0.217%

    No Known Activations