© 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. 6233
    Prev
    Next
    INDEX
    Explanations

    todo list management

    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
    iez
    -0.10
    绶
    -0.09
    伯
    -0.08
     lineup
    -0.08
    伦
    -0.08
     proceeds
    -0.08
    .AL
    -0.08
    è²Į
    -0.08
     Sala
    -0.07
    FER
    -0.07
    POSITIVE LOGITS
    ogne
    0.10
    åŃIJå¼¹
    0.10
    ardy
    0.10
    anten
    0.10
     Elegant
    0.09
    妨
    0.09
    åĪĨ解
    0.09
    æłĸ
    0.09
    奢
    0.09
    dress
    0.09
    Activations Density 0.099%

    No Known Activations