© 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. 772
    Prev
    Next
    INDEX
    Explanations

    symptoms of

    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
    wor
    -0.11
    æ¼ī
    -0.10
    注æĺİæĿ¥æºIJ
    -0.09
    amples
    -0.09
    лад
    -0.09
    ındaki
    -0.09
    umph
    -0.09
    æ²Ł
    -0.09
    urance
    -0.09
    Insn
    -0.09
    POSITIVE LOGITS
    atology
    0.13
    åĢĻ
    0.11
    ally
    0.10
    phony
    0.10
    çĺķ
    0.10
    åĻİ
    0.09
    ãģĵãģ¨ãģ§ãģĻ
    0.09
    带头人
    0.09
    ä¸ĩåįĥ
    0.09
    aje
    0.09
    Activations Density 0.034%

    No Known Activations