© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 55778
    Prev
    Next
    INDEX
    Explanations

    dot com or conference

    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
    åħ´
    -0.08
    妻
    -0.08
    åĬ©æīĭ
    -0.08
    ipl
    -0.08
    ç¬ijèĦ¸
    -0.08
    漫
    -0.08
    hash
    -0.07
    aise
    -0.07
    çĶŁæĹ¥
    -0.07
    Õ·
    -0.07
    POSITIVE LOGITS
    ernal
    0.10
    ä¸ĢåIJ¬
    0.09
    .addCell
    0.09
    pread
    0.09
     гол
    0.09
    ön
    0.09
    ä¸ĭ鼨
    0.08
    éħĿéħ¿
    0.08
    BuilderFactory
    0.08
    (optarg
    0.08
    Activations Density 0.010%

    No Known Activations