© 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. 4899
    Prev
    Next
    INDEX
    Explanations

    is commonly used or useful

    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
    éĢł
    -0.10
    éŨæĪ·
    -0.08
     обеÑģп
    -0.08
    æ»Ķ
    -0.08
    ä¸į代表
    -0.08
    ä¸īæĿ¡
    -0.08
    åĪĩæĸŃ
    -0.08
    åĿıäºĭ
    -0.08
    主ä½ĵ责任
    -0.08
    éĺħ读åħ¨æĸĩ
    -0.08
    POSITIVE LOGITS
    çĶ¨äºİ
    0.17
    çĶ¨æĿ¥
    0.15
     used
    0.14
    used
    0.14
    _used
    0.14
    .used
    0.13
     Used
    0.13
    主è¦ģçĶ¨äºİ
    0.13
     USED
    0.12
    Used
    0.12
    Activations Density 0.372%

    No Known Activations