© 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. 27422
    Prev
    Next
    INDEX
    Explanations

    year: count or number

    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
    æķ²
    -0.10
    æݨåĩºçļĦ
    -0.10
    LEC
    -0.09
    Spin
    -0.09
     Spin
    -0.09
    ero
    -0.09
    ä½İä¼°
    -0.09
    æĽ´å¤§çļĦ
    -0.09
    éri
    -0.09
    ANEL
    -0.09
    POSITIVE LOGITS
    æ´ģ
    0.09
    ä¸Ńæĸ°
    0.09
    åıĭ好
    0.09
    平衡
    0.09
    loth
    0.08
    åıijå±ķ缮æłĩ
    0.08
    çĶŁäº§æĢ»åĢ¼
    0.08
    شاب
    0.08
    壹
    0.08
     expectation
    0.08
    Activations Density 0.009%

    No Known Activations