© 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. 48662
    Prev
    Next
    INDEX
    Explanations

    Spanish and Italian food or culture

    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
    仪表
    -0.09
    itters
    -0.08
    ronics
    -0.08
     Missouri
    -0.08
    ri
    -0.08
     Merc
    -0.08
    lie
    -0.08
    erc
    -0.08
    bach
    -0.07
    缸äºĴ
    -0.07
    POSITIVE LOGITS
    æĬī
    0.10
    åħ¶å®ĥéĹ®é¢ĺ
    0.10
    帮ä»ĸ
    0.10
    é«ĺéĵģ
    0.10
    ç¾¤å²Ľ
    0.10
    æĮ½
    0.10
    ANTE
    0.09
    oland
    0.09
    车ä¸Ĭ
    0.09
    é«ĺä¸ī
    0.09
    Activations Density 0.001%

    No Known Activations