© 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. 58228
    Prev
    Next
    INDEX
    Explanations

    preparation and subsequent events

    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
    æ¨ĺ
    -0.11
    åıijå±ķè¶ĭåĬ¿
    -0.09
    ä¸įå¿ĺ
    -0.09
    æĬ¥éĶĢ
    -0.09
    ä¹ĭåĬ¿
    -0.09
    inish
    -0.09
    è¶ģ
    -0.09
    çİĩ
    -0.09
    åĿĢ
    -0.08
    欢è¿İæĤ¨
    -0.08
    POSITIVE LOGITS
    ä¼łæİĪ
    0.11
    åŁ¹
    0.11
    æķĻç»ĥ
    0.10
     coaching
    0.10
    æĶ¹è¿Ľ
    0.09
    yll
    0.09
    å¸ĥç½®
    0.09
     пÑĢид
    0.09
    éĨį
    0.09
     Coaching
    0.09
    Activations Density 0.050%

    No Known Activations