© 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. 822
    Prev
    Next
    INDEX
    Explanations

    Liverpool Football Club and City

    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
     riff
    -0.09
    oplast
    -0.08
    ep
    -0.08
    ÇĶ
    -0.08
    åĵģå¾·
    -0.08
    å±ī
    -0.08
     Swiss
    -0.07
    es
    -0.07
    ieg
    -0.07
    urm
    -0.07
    POSITIVE LOGITS
     lẽ
    0.10
    èĭ±çī¹
    0.10
     Haram
    0.10
    åĵĩ
    0.09
    utta
    0.09
    atten
    0.09
    ingle
    0.08
    沸
    0.08
    IDEOS
    0.08
    omo
    0.08
    Activations Density 0.009%

    No Known Activations