© 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. 3601
    Prev
    Next
    INDEX
    Explanations

    company, work, education, search

    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
    å¼ĢéĢļ
    -0.10
    aby
    -0.09
    被åĬ¨
    -0.08
    åīį端
    -0.08
    çªĪ
    -0.08
     PREF
    -0.08
    åīįåIJİ
    -0.07
    <=
    -0.07
     Front
    -0.07
    ä¸ĢèĪ¬çļĦ
    -0.07
    POSITIVE LOGITS
    âĸ¹
    0.11
    人æīįåŁ¹åħ»
    0.11
    èĭ¾
    0.10
    ÙĪØ«
    0.10
    æĩĭ
    0.09
     lecturer
    0.09
    ÑĢаÐ
    0.09
    óc
    0.09
    /drivers
    0.09
     Ñĩего
    0.09
    Activations Density 0.145%

    No Known Activations