© 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. 23608
    Prev
    Next
    INDEX
    Explanations

    village lies or is located

    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
    ä¸Ģæľµ
    -0.10
    è¿Ļ份
    -0.10
    åĴı
    -0.09
    è¿Ļå¼ł
    -0.09
     Mason
    -0.09
    æŃ¦å£«
    -0.09
    ä¸Ģå¼ł
    -0.08
    idi
    -0.08
    åĬłçĽĸ
    -0.08
    æĸ¥
    -0.08
    POSITIVE LOGITS
    æĿijåºĦ
    0.17
     villages
    0.15
    æĿijéķĩ
    0.15
    æĿijæ°ij
    0.14
     village
    0.14
    æĿijåŃIJ
    0.14
    æĿijèIJ½
    0.13
    æĿijæĿijæ°ij
    0.13
    æĿij
    0.13
    该æĿij
    0.13
    Activations Density 0.491%

    No Known Activations