© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52407
    Prev
    Next
    INDEX
    Explanations

    Nissan launches

    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
    éķ¿è¾¾
    -0.08
    åij½ä¸Ń
    -0.08
    ç»ıåİĨ
    -0.08
    åħ¨æĹ¥
    -0.08
    åĩ¤åĩ°
    -0.08
     bütün
    -0.08
     scale
    -0.08
    ç´IJ
    -0.08
    åį´åıĪ
    -0.08
    rox
    -0.08
    POSITIVE LOGITS
    ä¸į好
    0.10
    人æķ°
    0.10
    è§ĤæľĽ
    0.10
    ÑĹ
    0.09
    æ´»è·ĥ
    0.09
    ders
    0.09
    ä¾ł
    0.09
    vell
    0.09
    æĭ¥æĬ¤
    0.09
    etas
    0.09
    Activations Density 0.001%

    No Known Activations