© 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. 64029
    Prev
    Next
    INDEX
    Explanations

    back section or portion

    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
    igs
    -0.09
     занима
    -0.09
    eurs
    -0.08
    xious
    -0.08
    ius
    -0.08
    orda
    -0.08
    ç¼ĸ
    -0.08
    tion
    -0.08
    estion
    -0.08
    rolling
    -0.08
    POSITIVE LOGITS
    èļ¤
    0.10
    ç£ķ
    0.09
    åIJĦæľī
    0.09
    æĢ¡
    0.08
    å¾Īéķ¿
    0.08
    çķ
    0.08
    èł²
    0.08
    splash
    0.08
    红线
    0.08
    zens
    0.08
    Activations Density 0.032%

    No Known Activations