© 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. 33974
    Prev
    Next
    INDEX
    Explanations

    file extensions

    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
    éĢ¢
    -0.10
    Unnamed
    -0.09
    æ±ķ
    -0.09
    纸质
    -0.09
     ÑĢÑĥк
    -0.08
    èĵ¼
    -0.08
     desn
    -0.08
    ä¸įéľĢè¦ģ
    -0.08
     dul
    -0.08
    é²Ķ
    -0.08
    POSITIVE LOGITS
    çĻĸ
    0.12
    å¼ıçļĦ
    0.10
    æĬ¤èº«
    0.10
    æĸĩ件
    0.09
    顶端
    0.09
    åľ°æĸ¹æĶ¿åºľ
    0.09
    椿
    0.09
    æĬ¡
    0.09
    é£
    0.09
    æĪĸå¤ļ
    0.09
    Activations Density 0.285%

    No Known Activations