© 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. 1699
    Prev
    Next
    INDEX
    Explanations

    sales, career, gear, lessons, bio, talks

    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
    Native
    -0.08
    å°ijæķ°
    -0.08
    iss
    -0.08
    æĺĬ
    -0.08
    è¿Ķ
    -0.08
    æł¡åĽŃ
    -0.07
    ä¸ĸä¸Ĭ
    -0.07
    èĢ³è¾¹
    -0.07
     fancy
    -0.07
     Native
    -0.07
    POSITIVE LOGITS
    åĴĮ个人
    0.13
    èIJ
    0.11
    åĴĮ社ä¼ļ
    0.11
     ká»ĭch
    0.10
    ç²¾éĢļ
    0.10
    itivity
    0.09
    ä¹Łå¸ĮæľĽ
    0.09
    eps
    0.09
    yps
    0.09
    ä¸įä¸ĭ
    0.09
    Activations Density 0.680%

    No Known Activations