© 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. 8993
    Prev
    Next
    INDEX
    Explanations

    for you

    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
    驾
    -0.09
    ube
    -0.09
    çªį
    -0.09
    樱
    -0.08
    aska
    -0.08
    åŃ½
    -0.08
    Callbacks
    -0.08
    åĸĦ
    -0.08
    解读
    -0.08
    èİ·å¾ĹæĽ´å¤ļ
    -0.08
    POSITIVE LOGITS
    å¾Ĺèµ·
    0.11
    omen
    0.10
    åĵŃæ³£
    0.10
    à¹Ħหว
    0.10
    å¿į
    0.10
    寡
    0.10
    æŁ¿
    0.10
    ëĭĪëĭ¤
    0.09
    erial
    0.09
    ALES
    0.09
    Activations Density 0.087%

    No Known Activations