© 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. 56570
    Prev
    Next
    INDEX
    Explanations

    fruits, growth, development, quality

    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
    æĸĻ
    -0.08
    ẽ
    -0.08
    åı¯ä¿¡
    -0.08
    èĩªåĪ¶
    -0.08
    纡
    -0.08
    bare
    -0.08
    æĶ¾å¿ĥ
    -0.08
    å°ıèħ¿
    -0.08
     bare
    -0.08
    aise
    -0.08
    POSITIVE LOGITS
    第ä¸īèĢħ
    0.10
    åIJİæľŁ
    0.09
    第ä¸Ģ书记
    0.09
    ä½İ头
    0.09
    çł´æįŁ
    0.09
    æ¶Ł
    0.09
    缸èģļ
    0.09
    <TKey
    0.09
    bgcolor
    0.08
    ä¸Ŀè·¯
    0.08
    Activations Density 0.053%

    No Known Activations