© 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. 7274
    Prev
    Next
    INDEX
    Explanations

    limited programming experience

    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
    ä¸Ģ举
    -0.09
    æ¶ĪèĢĹ
    -0.09
    èį¡
    -0.09
    owered
    -0.08
    走访
    -0.08
    å®ķ
    -0.08
    ese
    -0.08
    æ¼Ķ
    -0.08
    ç¢İ
    -0.08
    西åĮĹ
    -0.08
    POSITIVE LOGITS
     влад
    0.10
     обÑĢаÑī
    0.09
    æĥŃ
    0.09
    ÑĤип
    0.09
    Ñīин
    0.09
    æı¿
    0.09
     Hein
    0.09
     ÙĨØŃÙĪ
    0.09
    sparse
    0.08
     Wort
    0.08
    Activations Density 0.136%

    No Known Activations