© 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. 17742
    Prev
    Next
    INDEX
    Explanations

    People's followed by Republic

    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
    带éĺŁ
    -0.10
    人群
    -0.09
    çķ´
    -0.09
    tte
    -0.09
     mens
    -0.09
    ventory
    -0.09
    ÑĢаÑģ
    -0.08
    人æīįåŁ¹åħ»
    -0.08
    finity
    -0.08
    çijģ
    -0.08
    POSITIVE LOGITS
    代表大ä¼ļ
    0.13
    解æĶ¾åĨĽ
    0.13
    大ä¼Ĺ
    0.11
    åħ¬ç¤¾
    0.10
    满æĦıçļĦ
    0.10
    nik
    0.09
     dụng
    0.09
    acing
    0.09
    é¢Ĩè¢ĸ
    0.09
    æ£Ģå¯ŁéĻ¢
    0.09
    Activations Density 0.044%

    No Known Activations