© 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. 17374
    Prev
    Next
    INDEX
    Explanations

    titles of films and hotels

    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
    ä¸Ģæĸ¹
    -0.09
    第
    -0.08
    å·¨åŀĭ
    -0.08
    æİ¥è¿ĩ
    -0.07
    è¦ģçľĭ
    -0.07
    ogen
    -0.07
     Conce
    -0.07
    大è§Ħ模
    -0.07
    _library
    -0.07
    compress
    -0.07
    POSITIVE LOGITS
    éŀŃ
    0.10
    /MM
    0.10
    ëĿ¼ëıĦ
    0.09
    anio
    0.09
    缸è§ģ
    0.09
     LENG
    0.09
    æ°´éĿ¢
    0.09
    稳
    0.09
    ç«¥
    0.09
    è·ª
    0.09
    Activations Density 0.005%

    No Known Activations