© 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. 18870
    Prev
    Next
    INDEX
    Explanations

    Auburn University

    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
    ware
    -0.09
    lep
    -0.09
    ../
    -0.09
    æ´ģåĩĢ
    -0.09
    ç¾İæ´²
    -0.08
    æŀģåĬĽ
    -0.08
     Trom
    -0.08
    éªł
    -0.08
    åħį
    -0.08
    å¸Ŀçİĭ
    -0.08
    POSITIVE LOGITS
    วà¸Ļ
    0.11
    ksen
    0.10
    ixon
    0.10
    å³Ĵ
    0.09
    vement
    0.09
    åŃĹæł·
    0.09
    åĪĨãģij
    0.09
    太太
    0.09
     Abbas
    0.09
     Clemson
    0.08
    Activations Density 0.007%

    No Known Activations