© 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. 11794
    Prev
    Next
    INDEX
    Explanations

    how or what

    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
    æīįè¡Į
    -0.10
    çļĦå°±æĺ¯
    -0.09
    æł¹æľ¬æ²¡æľī
    -0.08
     ÑģобÑģÑĤвенно
    -0.08
    MDB
    -0.08
    ãģ»ãģĨ
    -0.08
    æŃ£åĽłä¸º
    -0.08
    ä¸Ģæł·çļĦ
    -0.08
    æł¹æľ¬å°±ä¸į
    -0.08
    max
    -0.07
    POSITIVE LOGITS
    èĶĮ
    0.09
    ANNER
    0.09
    à¸Īำ
    0.09
    èĦĪ
    0.09
    æĪijè¿ĺæĺ¯
    0.09
    æĹĮ
    0.09
    trajectory
    0.09
    ç¢İçīĩ
    0.09
    .setTag
    0.08
    ä½łæĥ³
    0.08
    Activations Density 0.016%

    No Known Activations