© 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. 11229
    Prev
    Next
    INDEX
    Explanations

    second base, Google Glass, ecx register

    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
    ä¼ģ
    -0.09
    ä¿Ŀå®Ī
    -0.09
    ç¿ħèĨĢ
    -0.09
    æ½ľåľ¨
    -0.09
    éķ¿å¯¿
    -0.09
    è¢ĭ
    -0.08
     dow
    -0.08
     Conservative
    -0.08
    ç¾½
    -0.08
    ç¨ĭåºı
    -0.08
    POSITIVE LOGITS
    æŶæĬ¥
    0.11
    åıĸè¯ģ
    0.10
    è¦ģç´§
    0.09
    çIJ
    0.09
    åģļçļĦäºĭ
    0.09
    ä¸ĬçļĦ
    0.09
    èįIJ
    0.09
    ä¸įåıĹ
    0.09
    urer
    0.09
     abst
    0.09
    Activations Density 0.044%

    No Known Activations