© 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. 8154
    Prev
    Next
    INDEX
    Explanations

    internal RE, sustain ON, 00-5624

    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
    olib
    -0.10
    溱
    -0.09
    æĢ§åĪ«
    -0.09
    åĿIJçĿĢ
    -0.09
    yre
    -0.09
    éĩijèŀįæľįåĬ¡
    -0.09
    ä¸Ńå¼ı
    -0.09
    ä¹ŀ
    -0.08
    æ¬ł
    -0.08
    ä¸ŃèĢĥ
    -0.08
    POSITIVE LOGITS
    elsing
    0.09
    ä¸Ĭä¸ĭ
    0.09
    shan
    0.09
    åħ¥èĤ¡
    0.08
    iglia
    0.08
    åħ¥åĽŃ
    0.08
    è¿Ľ
    0.08
    è¡Į使
    0.08
    çł´ç¢İ
    0.08
    èīºæľ¯åĵģ
    0.08
    Activations Density 0.087%

    No Known Activations