© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 21222
    Prev
    Next
    INDEX
    Explanations

    controlled

    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
    æīĵçł´äºĨ
    -0.09
     spo
    -0.08
    è¯ķçĤ¹å·¥ä½ľ
    -0.08
    é£İ
    -0.08
    æĭ¯
    -0.08
    ä¸Ģå¤Ħ
    -0.08
    çľŁäºº
    -0.08
    åĭº
    -0.08
     blessed
    -0.08
    èij¡èIJĦ
    -0.08
    POSITIVE LOGITS
    ç¿ķ
    0.10
    ear
    0.09
    legs
    0.09
    ior
    0.09
    arus
    0.09
    led
    0.09
    ivet
    0.09
    ium
    0.09
    sure
    0.08
    åľ
    0.08
    Activations Density 0.008%

    No Known Activations