© 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. 17363
    Prev
    Next
    INDEX
    Explanations

    percentage of all

    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
    å¸ĮæľĽéĢļè¿ĩ
    -0.11
    зав
    -0.10
    æĺ¯æĪijçļĦ
    -0.10
    åħij
    -0.10
    天èĬ±
    -0.09
    æµģæ°ĵ
    -0.09
    èĥľä»»
    -0.09
    åIJĦèĩªçļĦ
    -0.09
    å¾Īå¤ļæľĭåıĭ
    -0.09
    ENTE
    -0.08
    POSITIVE LOGITS
    ej
    0.09
    Cols
    0.09
    å¨ĺ
    0.09
    deen
    0.08
    Ø´ÙĬ
    0.08
     program
    0.07
    骨
    0.07
     ÑģиÑĤ
    0.07
    èĮ¬
    0.07
    ани
    0.07
    Activations Density 0.012%

    No Known Activations