© 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. 10551
    Prev
    Next
    INDEX
    Explanations

    woven fabrics and yarn

    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
    asi
    -0.09
    éļı便
    -0.09
    æŁ¢
    -0.09
    å¤ĸå½¢
    -0.09
    èŀįåĮĸ
    -0.09
    å¡ijèĥ¶
    -0.09
    èĭ
    -0.08
    åĽ¢ç»ĵ
    -0.08
    èľķ
    -0.08
    å±Ī
    -0.08
    POSITIVE LOGITS
    ç»ĩ
    0.12
    æī¬
    0.10
    æĿ¼
    0.10
    ä¸Ŀ
    0.09
    ç¼ĸç»ĩ
    0.09
    ç¼¢
    0.09
    imps
    0.08
     маÑĪин
    0.08
    ä¸įä¸ĭ
    0.08
    èµĵ
    0.08
    Activations Density 0.041%

    No Known Activations