© 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. 4903
    Prev
    Next
    INDEX
    Explanations

    ckeditor.com or related software

    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
    骶
    -0.10
    è±ģ
    -0.09
    æĤħ
    -0.09
    èĪŁ
    -0.09
    ogonal
    -0.08
    纹
    -0.08
    æµĩ
    -0.08
    åĬ©æīĭ
    -0.08
    Chain
    -0.08
    ä¹ĸä¹ĸ
    -0.08
    POSITIVE LOGITS
    æķĸ
    0.10
    mur
    0.09
     Murray
    0.09
    Mur
    0.09
    é¢ľ
    0.08
     невоз
    0.08
    å¹´ä¸ŃåĽ½
    0.08
    åīįæľŁ
    0.08
     slic
    0.08
    å·¡è§Ĩ
    0.08
    Activations Density 0.062%

    No Known Activations