© 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. 62469
    Prev
    Next
    INDEX
    Explanations

    gmail.com addresses

    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
    orth
    -0.08
    gio
    -0.08
    ä¸Ģä½ĵ
    -0.08
    软
    -0.08
    ç¾İèģĶ
    -0.08
    Wr
    -0.08
    adio
    -0.08
    vent
    -0.08
    .ValidationError
    -0.08
     Fuji
    -0.07
    POSITIVE LOGITS
    åĬ¼
    0.11
    ussen
    0.09
    æľīæĦı
    0.09
    é©·
    0.09
    /commons
    0.09
    èģ¯åIJĪ
    0.09
    éķĽ
    0.09
    æĬ¡
    0.08
    æĥ³è¦ģ
    0.08
    æħ·æħ¨
    0.08
    Activations Density 0.029%

    No Known Activations