© 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. 27751
    Prev
    Next
    INDEX
    Explanations

    gratitude and praise

    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
    å¾Īå¤ļæľĭåıĭ
    -0.09
    contr
    -0.09
    åħ¬å¹³
    -0.09
    é²ľèĬ±
    -0.09
     latin
    -0.08
    å¸ĺ
    -0.08
    колÑĮ
    -0.08
    积
    -0.08
    ä¸ĢæŃ¥
    -0.08
    VC
    -0.08
    POSITIVE LOGITS
     CharSequence
    0.10
    æĴ¥
    0.09
    ulary
    0.09
    ä¸įå·²
    0.09
    isas
    0.09
     exempl
    0.08
    anke
    0.08
     Cel
    0.08
    ä¸įåıĹ
    0.08
    æĭ¨
    0.08
    Activations Density 0.011%

    No Known Activations