© 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. 40222
    Prev
    Next
    INDEX
    Explanations

    PCBs, lead, asbestos, CFCs, PBDEs

    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
    æĢħ
    -0.12
    ailer
    -0.11
    注å®ļ
    -0.10
     mest
    -0.10
    ä¸įèī¯
    -0.10
    åİ©
    -0.09
    esan
    -0.09
    ÑĤоÑĢ
    -0.09
    Squared
    -0.09
    ogl
    -0.09
    POSITIVE LOGITS
    ech
    0.11
    orbit
    0.09
    åŃĹåı·
    0.09
    çijŁ
    0.08
    bear
    0.08
    .au
    0.08
    cher
    0.08
     Calif
    0.08
    ish
    0.08
    ban
    0.07
    Activations Density 0.033%

    No Known Activations