© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6097
    Prev
    Next
    INDEX
    Explanations

    neo-

    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
    Negative Logits
     Noble
    -0.08
    å£ij
    -0.08
    yy
    -0.08
    åĴĮåľ°åĮº
    -0.08
    Unnamed
    -0.08
    weed
    -0.08
    acked
    -0.08
    ente
    -0.08
    âľħ
    -0.08
    cheid
    -0.07
    POSITIVE LOGITS
    merce
    0.10
    tsy
    0.10
    imize
    0.09
    ç¦ĭ
    0.09
    éºĤ
    0.09
    érie
    0.09
    luet
    0.09
    ocop
    0.09
    主ä¹īèĢħ
    0.09
    -era
    0.09
    Activations Density 0.033%

    No Known Activations