© 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. 11034
    Prev
    Next
    INDEX
    Explanations

    Venice and Vienna city names

    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
    sWith
    -0.11
    们çļĦ
    -0.09
    çĦ¶æĺ¯
    -0.09
    ship
    -0.09
    çīĮåŃIJ
    -0.09
    swith
    -0.09
    gee
    -0.09
    ãĢħ
    -0.09
    ÑģÑĤÑĮ
    -0.09
    们
    -0.09
    POSITIVE LOGITS
    èĥĢ
    0.09
    æĦıæĥ³ä¸įåĪ°
    0.09
    绶
    0.09
    oret
    0.09
    éħ¯
    0.09
    heimer
    0.09
    å¥Ĺè·¯
    0.08
    ucher
    0.08
    奥è¿IJä¼ļ
    0.08
    ç³ł
    0.08
    Activations Density 0.004%

    No Known Activations