© 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. 50243
    Prev
    Next
    INDEX
    Explanations

    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
    们
    -0.09
    ABCDEFG
    -0.09
    ä¹ĭ家
    -0.08
    æŀ¶åŃIJ
    -0.08
    ation
    -0.08
    бол
    -0.08
    严
    -0.08
    enstein
    -0.08
    å®ļå¾ĭ
    -0.08
    دا
    -0.08
    POSITIVE LOGITS
    oler
    0.09
    ếu
    0.09
    ä¸Ģ棵
    0.09
    ahead
    0.08
    ģı
    0.08
    s
    0.08
    ALES
    0.08
    ties
    0.08
    cake
    0.08
    ä¸Ģå¼ł
    0.08
    Activations Density 0.019%

    No Known Activations