© 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. 48405
    Prev
    Next
    INDEX
    Explanations

    clarifying statements

    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
    忽çĦ¶
    -0.09
    [at
    -0.09
    pedia
    -0.09
    [cur
    -0.09
     Liberation
    -0.08
    ä½łæĢİä¹Ī
    -0.08
     воÑĤ
    -0.08
    ìŀł
    -0.08
    ìĥĪ
    -0.08
     ê·¸ëŁ°ëį°
    -0.08
    POSITIVE LOGITS
    ä¸įæĺ¯
    0.12
    æĪijä¸įæĺ¯
    0.12
    åı¯ä¸įæĺ¯
    0.12
    并éĿŀ
    0.12
    并ä¸įæĺ¯
    0.11
    ä¸įæĺ¯ä¸Ģ个
    0.10
    è¿Ļä¸įæĺ¯
    0.10
    çļĦåīįæıIJä¸ĭ
    0.10
    ä¹Łä¸įæĺ¯
    0.10
    ä¸įåıªæĺ¯
    0.10
    Activations Density 0.034%

    No Known Activations