© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52247
    Prev
    Next
    INDEX
    Explanations

    various other

    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
     Fle
    -0.09
    éĥ½æĹłæ³ķ
    -0.09
    佯
    -0.09
    çļĦç»ıåİĨ
    -0.09
    容è²Į
    -0.09
    undy
    -0.08
    å½ĵåį³
    -0.08
    ä¸ĢçĽ´æ²¡æľī
    -0.08
    ä¹Łæĺ¯å¦ĤæѤ
    -0.08
    æIJĢ
    -0.08
    POSITIVE LOGITS
    åı¯ä¸įæĺ¯
    0.11
     ain
    0.11
    ãģ£ãģ¡ãĤĥ
    0.11
     pes
    0.10
    è±ĨèħIJ
    0.10
    åijĹ
    0.10
    妥
    0.10
    åķ¥
    0.09
    åĴ±
    0.09
     goodness
    0.09
    Activations Density 0.349%

    No Known Activations