© 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. 9578
    Prev
    Next
    INDEX
    Explanations

    duration or time measurement

    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
    åįĬ个æľĪ
    -0.09
    omit
    -0.09
    apos
    -0.09
    èīĩ
    -0.09
    åı¸ä»¤
    -0.09
    绺
    -0.09
    ç¾ģ
    -0.09
    ãģĦãģ¡
    -0.09
    iros
    -0.09
    ircuit
    -0.09
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.10
    侯
    0.09
    以ä¸ĬçļĦ
    0.09
    ouser
    0.09
    lier
    0.08
    ful
    0.08
    åĢĻ
    0.08
    glass
    0.08
    umi
    0.08
    oxy
    0.08
    Activations Density 0.020%

    No Known Activations