© 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. 36666
    Prev
    Next
    INDEX
    Explanations

    because of

    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
    çİĦ
    -0.10
    å¼ķãģį
    -0.09
    èµ°åĬ¿
    -0.09
     Trust
    -0.09
    ç®ķ
    -0.09
    侵害
    -0.09
     вÑģем
    -0.09
    ä¸ĵå¿ĥ
    -0.09
    奥
    -0.08
    æĪIJç«ĭ以æĿ¥
    -0.08
    POSITIVE LOGITS
    éĻ·
    0.10
    çļĦç¼ĺæķħ
    0.10
    itter
    0.09
    _tt
    0.09
    quina
    0.09
    ä¹°çļĦ
    0.09
    éģĹ
    0.09
    $$$$
    0.08
     reasons
    0.08
    unes
    0.08
    Activations Density 0.059%

    No Known Activations