© 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. 40065
    Prev
    Next
    INDEX
    Explanations

    stealing, stole, stolen, theft

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ually
    -0.11
    人士
    -0.09
    amen
    -0.09
    ual
    -0.09
    ãĥ³ãĤ°
    -0.09
    geh
    -0.08
    cake
    -0.08
    TURE
    -0.08
    imizer
    -0.08
    ding
    -0.08
    POSITIVE LOGITS
    Ìģ
    0.10
    ernet
    0.10
    OrUpdate
    0.10
    çļĦä¸ĢéĿ¢
    0.09
    åIJĦè¡Į
    0.09
    äºĨèµ·æĿ¥
    0.09
    ë¡Ń
    0.09
    imit
    0.09
    opes
    0.09
    ราย
    0.09
    Activations Density 0.009%

    No Known Activations