© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7137
    Prev
    Next
    INDEX
    Explanations

    present ideas

    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
    鼾
    -0.09
    ä¸Ģç»ı
    -0.09
    æ®ļ
    -0.09
    è·¨çķĮ
    -0.08
    åıijæĶ¹
    -0.08
    æ·Ģ
    -0.08
    å´®
    -0.08
    çŁŃæļĤ
    -0.08
    å¨Ħ
    -0.08
    éĺ¡
    -0.08
    POSITIVE LOGITS
    è¯Ĭ
    0.09
    æĹ¥å¸¸å·¥ä½ľ
    0.08
    _MACRO
    0.08
    æĦį
    0.08
    毫æĹł
    0.08
    åı¤åŁİ
    0.08
    好似
    0.08
    laughter
    0.07
     made
    0.07
    oppel
    0.07
    Activations Density 0.086%

    No Known Activations