© 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. 54826
    Prev
    Next
    INDEX
    Explanations

    SB, BB, IB, EB, VB, b

    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
    çļĦ姿æĢģ
    -0.08
    ohon
    -0.08
    plers
    -0.08
    ISTER
    -0.08
    pher
    -0.08
    arth
    -0.08
    âı
    -0.08
     Rover
    -0.08
    æĸĩåĮĸ建设
    -0.08
    arl
    -0.08
    POSITIVE LOGITS
    anded
    0.11
    jamin
    0.09
    çķĮ
    0.09
    å¿Ļç¢Į
    0.09
    å¸Ľ
    0.09
    çłŃ
    0.09
    ç³Ĭæ¶Ĥ
    0.09
    å½»åºķ
    0.09
    bots
    0.08
    æµij
    0.08
    Activations Density 0.167%

    No Known Activations