© 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. 3317
    Prev
    Next
    INDEX
    Explanations

    wanting or getting something

    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
    èĮĥ
    -0.08
    ä¸Ģ次æĢ§
    -0.08
    两åı¥
    -0.08
     unp
    -0.08
     Bow
    -0.08
     ÑģкаÑĩ
    -0.08
    ä¸Ģåı¥
    -0.08
    è¿Ļ个èģĮä¸ļ
    -0.07
    æģ»
    -0.07
     penn
    -0.07
    POSITIVE LOGITS
    å¾Ĺä¸įåĪ°
    0.12
    æīĢæıIJä¾Ľ
    0.11
    å¾ĹåĪ°äºĨ
    0.11
    å¾ĹåĪ°
    0.11
    åı¯ä»¥èİ·å¾Ĺ
    0.11
    GRAM
    0.11
    èİ·å¾ĹäºĨ
    0.11
     اÙĦØŃصÙĪÙĦ
    0.11
    éļıæīĭ
    0.10
    ç¨Ģ缺
    0.10
    Activations Density 0.077%

    No Known Activations