© 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. 30085
    Prev
    Next
    INDEX
    Explanations

    anARky

    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
    zych
    -0.10
    åıĭ好
    -0.09
    uala
    -0.09
    dre
    -0.08
    éªĮ
    -0.08
    flip
    -0.08
    acea
    -0.08
    éªĢ
    -0.08
    inki
    -0.08
     SetValue
    -0.08
    POSITIVE LOGITS
    å±¥
    0.09
     запиÑģи
    0.09
    iya
    0.09
    å·®å¼ĤåĮĸ
    0.08
    ä»İåīį
    0.08
    å¢ī
    0.08
    对èĩªå·±çļĦ
    0.08
    èİł
    0.08
    æĬĬèĩªå·±çļĦ
    0.08
    iously
    0.08
    Activations Density 0.061%

    No Known Activations