© 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. 8554
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

    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
    PropertyParams
    -0.11
    æĪijè¿ĺ
    -0.11
    å°Ĩæĺ¯
    -0.09
    éĢĨè¡Į
    -0.08
    printStats
    -0.08
    æĺİå¹´
    -0.08
    -inc
    -0.08
    åķ¼
    -0.08
    $header
    -0.08
    åIJİèĢħ
    -0.08
    POSITIVE LOGITS
    å¾Īå¤ļæŶåĢĻ
    0.11
    éĢļä¿Ĺ
    0.10
    æīĢ以æĪij们
    0.09
     поÑįÑĤомÑĥ
    0.09
    éĢļ常
    0.09
    è¿ĻçĤ¹
    0.09
    ä¸įåIJĮç¨ĭ度
    0.09
    åĽłæѤ
    0.09
     often
    0.08
    åŁºæľ¬çļĦãģ«
    0.08
    Activations Density 0.502%

    No Known Activations