© 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. 29943
    Prev
    Next
    INDEX
    Explanations

    broader/wider/larger

    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
    å¸ĪèĮĥ大åѦ
    -0.09
    详
    -0.09
    iec
    -0.09
    å°¤
    -0.09
    ç¿Ķ
    -0.09
    ru
    -0.09
    borg
    -0.08
    èŀį
    -0.08
    rael
    -0.08
     Concrete
    -0.08
    POSITIVE LOGITS
    æĦıä¹īä¸ĬçļĦ
    0.10
    anging
    0.09
    stä
    0.09
    éĢĤçĶ¨
    0.08
    社ä¼ļ责任
    0.08
    -than
    0.08
    -reaching
    0.08
    å¼ĢæĿ¥
    0.08
    egan
    0.08
    æĸĻ
    0.08
    Activations Density 0.018%

    No Known Activations