© 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. 64099
    Prev
    Next
    INDEX
    Explanations

    fitness pros, apps, and centers

    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
    ÑĩаÑĤ
    -0.11
    inding
    -0.09
    ÙĪØ·
    -0.09
    nder
    -0.08
    ffect
    -0.08
    ter
    -0.08
    OOD
    -0.08
    å§Ķå±Ī
    -0.08
    åĩ¡æĺ¯
    -0.08
    -too
    -0.08
    POSITIVE LOGITS
    çĶ¨åĵģ
    0.10
    scape
    0.10
    s
    0.10
    çĬ¶åĨµ
    0.09
    uart
    0.09
    olvers
    0.09
     Hath
    0.09
    sit
    0.09
    sport
    0.09
    sist
    0.09
    Activations Density 0.008%

    No Known Activations