© 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. 7819
    Prev
    Next
    INDEX
    Explanations

    BC following

    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
    éķ°
    -0.11
    ãģĹãģ¾ãģĨ
    -0.10
    ä¸ĸä¸Ĭ
    -0.09
    ä¸ĬäºĨ
    -0.08
     обÑıзаÑĤелÑĮ
    -0.08
    è°§
    -0.08
    à¸ĩาà¸Ļ
    -0.08
     Stap
    -0.08
    one
    -0.08
    .RestController
    -0.08
    POSITIVE LOGITS
    ç²¹
    0.10
    gary
    0.10
    lean
    0.10
    çĦ¶æĺ¯
    0.10
    DMI
    0.09
    oris
    0.09
    orsi
    0.09
    rames
    0.09
    ammen
    0.09
    raid
    0.08
    Activations Density 0.020%

    No Known Activations