© 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. 20871
    Prev
    Next
    INDEX
    Explanations

    storage

    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
    éĻĦ件
    -0.09
    stery
    -0.09
     rugged
    -0.09
    ÑĪий
    -0.09
    serter
    -0.08
    媪
    -0.08
    jee
    -0.08
    gro
    -0.08
    åħį责声æĺİ
    -0.08
    _globals
    -0.08
    POSITIVE LOGITS
    oho
    0.09
    lav
    0.09
     Bliss
    0.09
    -compatible
    0.08
    /Foundation
    0.08
    è¦ģçĶ¨
    0.08
    æĢĤ
    0.08
    请æķĻ
    0.08
    å®
    0.08
    itech
    0.08
    Activations Density 0.026%

    No Known Activations