© 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. 39786
    Prev
    Next
    INDEX
    Explanations

    game company 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
     Airbnb
    -0.09
    ç»ıæµİ社ä¼ļ
    -0.08
    è·Łå¥¹
    -0.08
    ç¬Ķè®°
    -0.08
     dạ
    -0.08
    å±¥èģĮ
    -0.08
    åħ±è¯Ĩ
    -0.08
     Flake
    -0.08
    黼
    -0.08
    åĽłä¸ºå¥¹
    -0.08
    POSITIVE LOGITS
    åıijåĶ®
    0.12
    å¼ĢåıijèĢħ
    0.11
    å¼Ģåıij
    0.11
    åľ¨æ¸¸æĪıä¸Ń
    0.10
    è¯Ħæµĭ
    0.09
     game
    0.09
    ç¾İæľ¯
    0.09
    æŀķ
    0.09
     developers
    0.09
    游æĪı
    0.08
    Activations Density 0.620%

    No Known Activations