© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 33626
    Prev
    Next
    INDEX
    Explanations

    describing teams or leagues

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä¼Ĺ
    -0.10
     Burk
    -0.09
    åĨ·éĿĻ
    -0.09
    èģĮåijĺ
    -0.09
    ä¸ĭ车
    -0.09
     Specialists
    -0.08
    .family
    -0.08
    ä½ľä¸ļ
    -0.08
    æĺ¨æĹ¥
    -0.08
     mad
    -0.08
    POSITIVE LOGITS
    åĬŀåѦ
    0.11
    èIJ½æĪ·
    0.10
    åĬŀ
    0.10
    çļĦåŁİå¸Ĥ
    0.10
    åľ°åŁŁ
    0.10
     hosting
    0.10
    åľ°çIJĨä½įç½®
    0.10
    éĢīåĿĢ
    0.10
     Fever
    0.09
    çģŃ亡
    0.09
    Activations Density 0.183%

    No Known Activations