© 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. 12192
    Prev
    Next
    INDEX
    Explanations

    hr mann

    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
    clang
    -0.09
    usz
    -0.09
    posing
    -0.09
    Hier
    -0.09
    psilon
    -0.09
    åŃ©
    -0.09
     дÑĥÑħ
    -0.09
    桧
    -0.09
    ENSE
    -0.08
     histo
    -0.08
    POSITIVE LOGITS
    acter
    0.10
    reuse
    0.10
    ened
    0.09
    utterstock
    0.09
    iniz
    0.09
    osoph
    0.09
    editary
    0.09
    soever
    0.09
    iest
    0.09
    èĢģ人家
    0.09
    Activations Density 0.171%

    No Known Activations