© 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. 63798
    Prev
    Next
    INDEX
    Explanations

    legal rights

    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
    èµŀ
    -0.12
    顶å±Ĥ
    -0.11
    è®ļ
    -0.10
    plat
    -0.09
    追éļı
    -0.09
    íĮIJ
    -0.09
    èµŀæī¬
    -0.08
    çĺ«
    -0.08
    èµŀç¾İ
    -0.08
    æ¦ľ
    -0.08
    POSITIVE LOGITS
    æĿĥçĽĬ
    0.27
     rights
    0.21
    æĿĥåĪ©
    0.21
    åIJĪæ³ķæĿĥçĽĬ
    0.20
     пÑĢава
    0.19
    æ¬ĬçĽĬ
    0.19
    Rights
    0.18
     Rights
    0.18
    çļĦæĿĥåĪ©
    0.17
    rights
    0.15
    Activations Density 0.043%

    No Known Activations