© 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. 58392
    Prev
    Next
    INDEX
    Explanations

    identification

    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
    Ñħи
    -0.09
    èµ·ä¼ı
    -0.09
    etime
    -0.09
    æĬ¤æłı
    -0.08
    çĥŃ度
    -0.08
    é¢Ĭ
    -0.08
    аÑĢи
    -0.08
    çŁ£
    -0.08
    ãĤĵãģª
    -0.08
    omba
    -0.07
    POSITIVE LOGITS
    æĺ¯è°ģ
    0.11
    对åºĶ
    0.11
     unl
    0.10
    è¯ĨåĪ«
    0.10
    è°ģ
    0.10
     identification
    0.10
    身份
    0.10
    对åºĶçļĦ
    0.09
     label
    0.09
     Identification
    0.09
    Activations Density 0.196%

    No Known Activations