© 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. 6115
    Prev
    Next
    INDEX
    Explanations

    one followed by click or line

    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
    åĭ¾
    -0.12
    åı¯æĥ³èĢĮçŁ¥
    -0.09
    AtA
    -0.09
    otros
    -0.09
    nt
    -0.08
    Ñĩик
    -0.08
    elpers
    -0.08
    ETS
    -0.08
    秽
    -0.08
    gn
    -0.08
    POSITIVE LOGITS
    ä¸ĢåĪĢ
    0.11
    æIJ¬
    0.10
     полÑĥ
    0.10
    ç±³ç²ī
    0.09
    ä¹łæĥ¯äºĨ
    0.09
    æ²Ļ
    0.09
    Bat
    0.09
    æ²Ļ滩
    0.09
    ä¸Ģ件äºĭ
    0.09
    ç½ijéĢļ
    0.09
    Activations Density 0.067%

    No Known Activations