© 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. 49441
    Prev
    Next
    INDEX
    Explanations

    location names and streets

    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
    eut
    -0.09
    æľīæĿ¡ä»¶çļĦ
    -0.09
    å®Ī
    -0.09
    ERICA
    -0.09
     Opr
    -0.09
    æĪª
    -0.08
    emd
    -0.08
    ä¸ĸä¿Ĺ
    -0.08
    วà¸Ķ
    -0.08
    åħħåĪĨåĪ©çĶ¨
    -0.08
    POSITIVE LOGITS
    æŀķ头
    0.10
    çĸijä¼¼
    0.09
    çĶ¨äºº
    0.09
    é«ĺä½İ
    0.09
    æ¶ī
    0.09
    ä¸Ŀè·¯
    0.09
    ç§ijæĬĢåĪĽæĸ°
    0.08
     Alg
    0.08
    ä»Ĭ天æĪij们
    0.08
     vicinity
    0.08
    Activations Density 0.083%

    No Known Activations