© 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. 650
    Prev
    Next
    INDEX
    Explanations

    Bryan, Bowie, ryan, ian names

    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
    ë¡ł
    -0.10
     Ride
    -0.10
    halb
    -0.10
    ness
    -0.09
    uet
    -0.09
    ster
    -0.09
    ital
    -0.09
    verständlich
    -0.09
    HeaderValue
    -0.09
    ç¡®åĪĩ
    -0.09
    POSITIVE LOGITS
    aceous
    0.11
    ëģĶ
    0.10
    elper
    0.09
    asty
    0.09
    orld
    0.09
    鬲
    0.09
    AYER
    0.08
    AMP
    0.08
    arning
    0.08
     dioxide
    0.08
    Activations Density 0.005%

    No Known Activations