© 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. 56348
    Prev
    Next
    INDEX
    Explanations

    award or honor

    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
    plier
    -0.10
    空çĻ½
    -0.10
    çĶļ
    -0.09
    moz
    -0.09
    iculty
    -0.09
    æľªæĪIJ
    -0.09
    æ¯ıæ¯ı
    -0.08
    ricks
    -0.08
    etak
    -0.08
    çľĭä¼¼
    -0.08
    POSITIVE LOGITS
    mah
    0.09
    ä¸Ģ个æĸ°çļĦ
    0.09
    ué
    0.09
    cor
    0.09
    à¸ij
    0.09
    æĪijæł¡
    0.08
    ť
    0.08
    èĩ³æѤ
    0.08
    äºĨä¸Ģ个
    0.08
    alah
    0.08
    Activations Density 0.023%

    No Known Activations