© 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. 64125
    Prev
    Next
    INDEX
    Explanations

    under the

    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
    pery
    -0.12
    -0.10
    adesh
    -0.10
    tery
    -0.09
    iling
    -0.09
    èĩ³äºİ
    -0.09
    vos
    -0.09
    ÑĤеÑĢ
    -0.09
    ops
    -0.09
    unread
    -0.09
    POSITIVE LOGITS
    neath
    0.22
    whelming
    0.15
    stood
    0.15
    lined
    0.15
    lying
    0.15
    lies
    0.13
    lining
    0.12
     Äijá»±ng
    0.12
    ÑĤвеÑĢж
    0.12
    cooked
    0.12
    Activations Density 0.116%

    No Known Activations