© 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. 40173
    Prev
    Next
    INDEX
    Explanations

    betting

    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
    褥
    -0.10
    (SIG
    -0.09
    æªĢ
    -0.09
     assignable
    -0.09
    人寿
    -0.09
     cargo
    -0.08
    ayette
    -0.08
    åıĪ好
    -0.08
    çĭ¸
    -0.08
    arning
    -0.08
    POSITIVE LOGITS
    uell
    0.10
     mest
    0.09
    gest
    0.09
    æĿijåºĦ
    0.09
    ben
    0.09
     пеÑĢев
    0.08
    iphy
    0.08
    åIJĪçIJĨçļĦ
    0.08
    riad
    0.08
     millions
    0.08
    Activations Density 0.008%

    No Known Activations