© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19987
    Prev
    Next
    INDEX
    Explanations

    attempt at

    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
    è§ģè¿ĩ
    -0.09
    åĸĦäºİ
    -0.09
    ales
    -0.08
    æŃ¤äºº
    -0.08
    ä¸Ĭå¸Ŀ
    -0.08
    ä¸įæĸŃåľ°
    -0.08
    åĨ¢
    -0.08
    ettes
    -0.08
    alez
    -0.08
    èĽŃ
    -0.08
    POSITIVE LOGITS
    0.09
     paren
    0.09
    ä»Ļ
    0.08
    æĪIJ为ä¸ĢåIJį
    0.08
    tle
    0.08
    å®Ŀè´Ŀ
    0.08
    æĪIJ为ä¸Ģ个
    0.08
     pare
    0.08
    ernal
    0.08
    artz
    0.08
    Activations Density 0.017%

    No Known Activations