© 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. 17152
    Prev
    Next
    INDEX
    Explanations

    for purposes of

    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
    æī¾åĪ°äºĨ
    -0.10
    ëŀij
    -0.09
    зам
    -0.09
    大åŁİå¸Ĥ
    -0.09
    è°ľ
    -0.09
    å¨ĩ
    -0.09
    биÑĢ
    -0.08
    ä¸¤å¼ł
    -0.08
     اÙĦÙĥÙĦ
    -0.08
    å¬
    -0.08
    POSITIVE LOGITS
    .getvalue
    0.10
     testing
    0.09
    ç§ijåѦçłĶ究
    0.09
     purposes
    0.09
    éĺħ读
    0.08
    cke
    0.08
    éħįåIJĪ
    0.08
    testing
    0.08
     purpose
    0.08
    bidden
    0.08
    Activations Density 0.257%

    No Known Activations