© 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. 60571
    Prev
    Next
    INDEX
    Explanations

    sports teams

    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
    SharedPtr
    -0.10
    cer
    -0.09
    emu
    -0.09
    æ¯įæł¡
    -0.09
     nieu
    -0.09
    cpy
    -0.09
    tep
    -0.08
    ç¯Ļ
    -0.08
    å¸ĪèµĦ
    -0.08
    AdapterFactory
    -0.08
    POSITIVE LOGITS
    bones
    0.10
    rü
    0.09
    oints
    0.09
    0.08
    lector
    0.08
    åĻ
    0.08
    ulet
    0.08
    rish
    0.08
     Ñģобой
    0.08
    çĤī
    0.08
    Activations Density 0.003%

    No Known Activations