© 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. 62924
    Prev
    Next
    INDEX
    Explanations

    phrase that indicates a statement of current status or location

    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
    éĤ£ä¸ªæŶåĢĻ
    -0.12
    éĤ£æŶåĢĻ
    -0.11
    éĤ£æŶ
    -0.10
    éĤ£æ¬¡
    -0.10
    .prof
    -0.09
    çĦķ
    -0.09
    éĬ
    -0.09
    çĸij
    -0.08
    apter
    -0.08
    çĶ¸
    -0.08
    POSITIVE LOGITS
    ä»Ĭ天çļĦ
    0.14
    æѤåĪ»
    0.13
    æĺİ天
    0.11
    ä»Ĭ天
    0.10
     tonight
    0.10
     today
    0.09
     ÑģейÑĩаÑģ
    0.09
    ä»ĬæĻļ
    0.09
    æĺİæĹ¥
    0.09
    åĨĻçĿĢ
    0.09
    Activations Density 0.100%

    No Known Activations