© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 54051
    Prev
    Next
    INDEX
    Explanations

    to [verb]

    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
    èĥ½è®©
    -0.13
    èĥ½ä½¿
    -0.10
    åİ»äºĨ
    -0.10
    ç»ĻäºĨæĪij
    -0.10
    çľĭ好
    -0.10
    èĥ½æ»¡è¶³
    -0.10
    åı¯ä»¥å¸®åĬ©
    -0.10
    ç»ĻäºĨ
    -0.09
    èĥ½åľ¨
    -0.09
    åĩĨå¤ĩ好
    -0.09
    POSITIVE LOGITS
    窥
    0.10
    æĽ´å¥½åľ°
    0.09
    /us
    0.09
    elf
    0.09
    ä¸įå¿ħ
    0.09
    æľĢ大éĻIJ度
    0.09
    å½ĵä¹ĭæĹłæĦ§
    0.09
    åĸĺ
    0.08
    /her
    0.08
    缴æİ¥
    0.08
    Activations Density 0.050%

    No Known Activations