© 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. 4936
    Prev
    Next
    INDEX
    Explanations

    place names and proper nouns

    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
    强èĢħ
    -0.10
    istr
    -0.09
    acy
    -0.09
    ç¥ĸ
    -0.09
    竺
    -0.08
    _pdata
    -0.08
    quez
    -0.08
    æ¯ıä¸Ģ次
    -0.08
    бо
    -0.08
    åĽ½å®¶æĪĺçķ¥
    -0.08
    POSITIVE LOGITS
    ÑģÑĮ
    0.09
    享
    0.08
    èĽ®
    0.08
    alom
    0.08
    è¾°
    0.08
    æīĢæīĢ
    0.08
    大åıĶ
    0.08
    ynet
    0.07
     cler
    0.07
    è¯Ŀ
    0.07
    Activations Density 0.925%

    No Known Activations