© 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. 11608
    Prev
    Next
    INDEX
    Explanations

    physical component or surface

    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°±æľīäºĨ
    -0.08
    æľ¬æĿ¥å°±
    -0.08
    gang
    -0.08
    åIJŀåĻ¬
    -0.08
    PIO
    -0.08
    æĭ¥æĮ¤
    -0.08
    人çĶŁ
    -0.08
    æķĪ
    -0.08
    eron
    -0.08
    jes
    -0.08
    POSITIVE LOGITS
    ä½Ĩæĺ¯åľ¨
    0.09
    có
    0.08
    .opend
    0.08
    åľ¨è¿Ļç§į
    0.08
    à¤Ľ
    0.08
     oppos
    0.08
    åħħè£ķ
    0.08
    ä¸Ńå¤ĸ
    0.08
    æ±ŁéŨ
    0.08
    åľ¨åħ¶
    0.08
    Activations Density 0.704%

    No Known Activations