© 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. 5520
    Prev
    Next
    INDEX
    Explanations

    an or a followed by word

    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
    ç£ħ
    -0.10
    pics
    -0.09
     Charm
    -0.09
    å¥ĸåѦ
    -0.08
    ä¸Ģç³»åĪĹ
    -0.08
    ç³»åĪĹ
    -0.08
    æ»ĭåij³
    -0.08
    ëĭ¤ê°Ģ
    -0.08
    complete
    -0.08
     Sag
    -0.08
    POSITIVE LOGITS
    éĢļè¡Į
    0.10
    åĿŁ
    0.09
    ç¢Ł
    0.09
    ãĤ¸ãĥ¼
    0.09
    ercul
    0.08
    åĽłä¸ºåľ¨
    0.08
    仵
    0.08
    ç«ĭåľº
    0.08
    å¢ĵ
    0.08
    ä¼ģä¸ļåĴĮ
    0.08
    Activations Density 0.014%

    No Known Activations