© 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. 32599
    Prev
    Next
    INDEX
    Explanations

    OMG!

    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
    zelf
    -0.10
    aget
    -0.09
     Sadd
    -0.09
    ä¸įæŃ»
    -0.08
    YPE
    -0.08
    atre
    -0.08
    满äºĨ
    -0.08
    é²ŀ
    -0.08
    imator
    -0.08
    ocks
    -0.08
    POSITIVE LOGITS
    sWith
    0.11
    å·¨æĺŁ
    0.09
    unt
    0.09
     Insider
    0.08
    宪
    0.08
    æĸ°èĤ¡
    0.08
    uby
    0.08
    çĴł
    0.08
    uset
    0.08
    лем
    0.08
    Activations Density 0.001%

    No Known Activations