© 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. 4590
    Prev
    Next
    INDEX
    Explanations

    sports game contexts

    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
    æī¿
    -0.10
    ç»ķ
    -0.10
    磨æįŁ
    -0.09
    ders
    -0.09
     ÑĢÑĥб
    -0.08
    亲åĪĩ
    -0.08
    äºĨ解ä¸Ģä¸ĭ
    -0.08
    oni
    -0.08
    ä¸įæĸŃå¢ŀåĬł
    -0.08
    ãĥªãĤ¢
    -0.08
    POSITIVE LOGITS
    åıijæĮ¥
    0.11
     Kemp
    0.10
    岸
    0.10
    åijĬåĪ«
    0.09
     ÑģебÑı
    0.09
    ä¸įä¹ı
    0.09
    çĻ¼æı®
    0.09
    å¾Ĺèµ·
    0.09
    æ¼¾
    0.09
    å·
    0.09
    Activations Density 0.022%

    No Known Activations