© 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. 2477
    Prev
    Next
    INDEX
    Explanations

    his / its / it

    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
    ứ
    -0.10
    å¿ĥå¢ĥ
    -0.10
    åѦä¼ļ
    -0.09
    çķħéĢļ
    -0.09
    éĤ£ç§į
    -0.09
    ystack
    -0.09
    å·¥ä½ľäººåijĺ
    -0.09
    DMIN
    -0.09
    çļĦå¿ĥæĥħ
    -0.09
     Rooney
    -0.09
    POSITIVE LOGITS
    ä»ĸçļĦ
    0.11
     his
    0.10
    她çļĦ
    0.09
    她æĺ¯
    0.09
    ä»ĸæĺ¯
    0.09
    akes
    0.09
    ä»ĸæĺ¯ä¸Ģ个
    0.09
    æĬĬä»ĸ
    0.09
    çľĭä»ĸ
    0.08
    enstein
    0.08
    Activations Density 0.100%

    No Known Activations