© 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. 6249
    Prev
    Next
    INDEX
    Explanations

    affecting change

    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
    yu
    -0.10
    æ¸Į
    -0.09
    å¿Ŀ
    -0.09
    ounter
    -0.09
    ran
    -0.09
    ç«ł
    -0.08
    å¸Ń
    -0.08
    app
    -0.08
    çĦ¦çĤ¹
    -0.08
    rint
    -0.08
    POSITIVE LOGITS
    åıĺéĿ©
    0.20
     change
    0.17
     Change
    0.16
    change
    0.14
    Change
    0.14
    .change
    0.14
    _change
    0.13
    (change
    0.13
     CHANGE
    0.13
    åıĺåĮĸ
    0.13
    Activations Density 0.067%

    No Known Activations