© 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. 26585
    Prev
    Next
    INDEX
    Explanations

    professional and its contexts

    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
    çªĿ
    -0.11
    åıĮèµ¢
    -0.09
    ẹ
    -0.09
    èĢĥéªĮ
    -0.08
     Rupert
    -0.08
    羣çIJĨ
    -0.08
    ä»İä¸ļ
    -0.08
    _dropout
    -0.08
    soever
    -0.08
    竣工
    -0.08
    POSITIVE LOGITS
    wort
    0.09
    é¼IJ
    0.09
    åĴĮ社ä¼ļ
    0.09
    ully
    0.09
    .Exec
    0.08
    人士
    0.08
    åħ³ç³»
    0.08
    å£°éŁ³
    0.08
    ga
    0.08
    .plus
    0.08
    Activations Density 0.015%

    No Known Activations