© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37900
    Prev
    Next
    INDEX
    Explanations

    involved in

    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
    ï¸
    -0.10
    宥
    -0.10
    нÑĮ
    -0.09
    noch
    -0.09
    ýt
    -0.08
    æľĢæĸ°çļĦ
    -0.08
    çļĭ
    -0.08
    Ordinal
    -0.08
    enen
    -0.08
    ä¸ĥæľĪ
    -0.08
    POSITIVE LOGITS
    æĢ»æĺ¯
    0.13
    åĸĦäºİ
    0.11
    ä»İæĿ¥ä¸į
    0.11
    ä¸ĢåIJij
    0.11
    ä¸Ģè´¯
    0.11
     вÑģегда
    0.11
    總æĺ¯
    0.11
    åİĨæĿ¥
    0.11
    ä»İæĿ¥
    0.10
     altijd
    0.10
    Activations Density 0.105%

    No Known Activations