© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8219
    Prev
    Next
    INDEX
    Explanations

    arrival or appearance on scene

    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
    éĴ°
    -0.10
    wor
    -0.09
    离
    -0.09
     Welch
    -0.08
    泪
    -0.08
    工夫
    -0.08
     вÑĭполнен
    -0.08
     Mason
    -0.08
    aris
    -0.07
     Sapphire
    -0.07
    POSITIVE LOGITS
    çļĦåĪ°æĿ¥
    0.20
    è¿ĽæĿ¥
    0.19
    æĿ¥äºĨ
    0.18
    åĪ°æĿ¥
    0.16
    æĿ¥ä¸´
    0.16
    åĩºæĿ¥
    0.15
    æĿ¥è¢Ń
    0.13
    éĹ®ä¸ĸ
    0.13
     arrival
    0.13
    ä»ĭåħ¥
    0.13
    Activations Density 0.088%

    No Known Activations