© 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. 9113
    Prev
    Next
    INDEX
    Explanations

    fish and fishes

    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
    dsn
    -0.10
    ÙĨÙĪ
    -0.10
     dust
    -0.09
    ëijĺ
    -0.09
    orio
    -0.09
    оÑī
    -0.08
    >Type
    -0.08
    asion
    -0.08
    æĮij
    -0.08
    代
    -0.08
    POSITIVE LOGITS
    erman
    0.14
    鱼类
    0.11
    ðŁIJŁ
    0.11
    ermen
    0.10
    é±¼
    0.10
     fishes
    0.10
    æ¡ģ
    0.10
    鲫
    0.09
    èĦį
    0.09
    èĵĿ天
    0.09
    Activations Density 0.056%

    No Known Activations