© 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. 26343
    Prev
    Next
    INDEX
    Explanations

    Daily News and Daily Beast

    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
    大家ä¸Ģèµ·
    -0.09
    æľīçļĦ
    -0.09
    ?key
    -0.09
    aal
    -0.08
    éģIJ
    -0.08
    éĻī
    -0.08
    åĭĻ
    -0.08
    ivial
    -0.08
    åĿ¨
    -0.08
    西äºļ
    -0.08
    POSITIVE LOGITS
    åı£åij³
    0.09
    æĹ©æĻ¨
    0.09
    è·Łè¿Ľ
    0.09
    lop
    0.08
    ä¸Ģåı£
    0.08
    ruptcy
    0.08
    æ»ĭåij³
    0.08
    éĹº
    0.08
    æĶ¶æķĽ
    0.08
    æĸij
    0.08
    Activations Density 0.023%

    No Known Activations