© 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. 1440
    Prev
    Next
    INDEX
    Explanations

    operating systems and software

    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
    åĿ¦
    -0.10
    å±ķä½į
    -0.09
    ä»Ģä¹Īä¸ľè¥¿
    -0.09
    èĪŁ
    -0.08
    æ½ĩ
    -0.08
     stuff
    -0.08
    åIJĪèµĦ
    -0.08
    åķĨåĬ¡éĥ¨
    -0.08
    itory
    -0.08
    bir
    -0.08
    POSITIVE LOGITS
    æľīäºĨ
    0.14
    æľ¬èº«çļĦ
    0.13
    æľ¬èº«
    0.11
    åı²ä¸Ĭ
    0.10
    çļĦä¸įåIJĮ
    0.09
    SelectionMode
    0.09
    æĢ»éĩı
    0.09
    å°±æľīäºĨ
    0.09
     itself
    0.08
    /goto
    0.08
    Activations Density 0.279%

    No Known Activations