© 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. 11371
    Prev
    Next
    INDEX
    Explanations

    a followed by job, local, or scripting

    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
    åħ¨éĿ¢æİ¨è¿Ľ
    -0.09
    etch
    -0.09
    ìŀĩ
    -0.09
    å¥ł
    -0.08
    ä»ĬçĶŁ
    -0.08
    积æŀģå¼Ģå±ķ
    -0.08
    æľ¬æľŁ
    -0.08
    æĸ°ä¸Ģ代
    -0.08
     ÙĪعÙĨ
    -0.08
    åªļ
    -0.08
    POSITIVE LOGITS
     hum
    0.09
    æ³±
    0.09
    ä¸ĢéĹª
    0.09
    éķ¿è¿ľ
    0.09
    oly
    0.08
    殿åłĤ
    0.08
    hub
    0.08
    黣
    0.08
     Pant
    0.08
    _wrong
    0.08
    Activations Density 0.369%

    No Known Activations