© 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. 60633
    Prev
    Next
    INDEX
    Explanations

    UD

    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
     lẽ
    -0.11
     ÑĥÑĩаÑģÑĤ
    -0.10
    ãģĦãĤĮãģ°
    -0.09
    è¿Ļæł·æīįèĥ½
    -0.09
    ãģĩ
    -0.09
    éĤĢ
    -0.09
    éĥ¨åĪĨåĨħ容
    -0.09
    thon
    -0.09
    åĤ©
    -0.09
    itud
    -0.09
    POSITIVE LOGITS
    apest
    0.09
    áºŃn
    0.09
    idian
    0.09
    locker
    0.08
    prints
    0.08
    printed
    0.08
    à¸Īำ
    0.08
    Endian
    0.08
    ì§ľ
    0.08
    çīĩåŃIJ
    0.08
    Activations Density 0.017%

    No Known Activations