© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 24323
    Prev
    Next
    INDEX
    Explanations

    Howard followed by names or places

    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
    ../../../
    -0.19
    ../../
    -0.14
    ulator
    -0.10
    zelf
    -0.10
    uses
    -0.10
    累累
    -0.10
    çģ¶
    -0.09
    éĵĽ
    -0.09
    ../../../../
    -0.09
    urally
    -0.09
    POSITIVE LOGITS
    t
    0.10
    IgnoreCase
    0.10
     ë¶Ī구íķĺê³ł
    0.10
    åľ¨äº¬
    0.09
    ãĤ
    0.09
    anded
    0.09
    enance
    0.09
    ie
    0.09
    sville
    0.09
    ering
    0.09
    Activations Density 0.008%

    No Known Activations