© 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. 47411
    Prev
    Next
    INDEX
    Explanations

    alive.alive

    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
    à¹Į
    -0.10
    ised
    -0.10
    æŨ
    -0.10
    acles
    -0.10
    lake
    -0.10
    acular
    -0.09
    ulos
    -0.09
    older
    -0.09
    ese
    -0.09
    erator
    -0.09
    POSITIVE LOGITS
    åĭĥåĭĥ
    0.11
    ye
    0.10
    ä¸İåIJ¦
    0.09
    èµĺ
    0.09
    åıĪ好
    0.09
    kin
    0.09
    é¾Ī
    0.09
    æĻ°
    0.09
    çļĦåľ°æĸ¹
    0.09
    entic
    0.09
    Activations Density 0.011%

    No Known Activations