© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 948
    Prev
    Next
    INDEX
    Explanations

    to followed by verbs

    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
    累累
    -0.10
    åľ¨æĦı
    -0.10
    æĪij认为
    -0.09
    .CG
    -0.09
    æĸĻ
    -0.09
    çŀŃ
    -0.09
    åľ¨æĪijçľĭæĿ¥
    -0.09
    失è°ĥ
    -0.09
    anson
    -0.08
    .CommandType
    -0.08
    POSITIVE LOGITS
    åĢŁæѤ
    0.11
    念头
    0.09
    æĺİçĻ½äºĨ
    0.09
    åIJ¬åIJ¬
    0.09
    åĩŃåĢŁçĿĢ
    0.09
    以æѤ
    0.08
    çľĭçľĭ
    0.08
    æĻĵå¾Ĺ
    0.08
    èģĬèģĬ
    0.08
    åħ¥åı£
    0.08
    Activations Density 0.091%

    No Known Activations