© 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. 23607
    Prev
    Next
    INDEX
    Explanations

    imminent or approaching dates

    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
    dig
    -0.09
    åģļå¾Ĺ
    -0.09
    åĩ¹
    -0.09
    ä¸į足
    -0.09
    åŁºç¡Ģä¸Ĭ
    -0.08
    æĮĸæİĺ
    -0.08
    çļĦåŁºç¡Ģä¸Ĭ
    -0.08
    æ³ŀ
    -0.08
    æĸ°çĶŁ
    -0.08
    æľĿçĿĢ
    -0.08
    POSITIVE LOGITS
    çļĦåĪ°æĿ¥
    0.20
    åĪ°æĿ¥
    0.17
    æĿ¥ä¸´
    0.15
    åį³å°ĨåĪ°æĿ¥
    0.15
    çļĦèĦļæŃ¥
    0.11
    ä¸įåı¯éģ¿åħį
    0.11
    éĻį临
    0.11
    éĤ£ä¸Ģ天
    0.11
     inevitable
    0.11
    åĪ°æŶåĢĻ
    0.11
    Activations Density 0.086%

    No Known Activations