© 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. 3079
    Prev
    Next
    INDEX
    Explanations

    mailto:

    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
    adin
    -0.09
    缩
    -0.09
     blogger
    -0.09
    éĺħ读åħ¨æĸĩ
    -0.08
     cá»ķ
    -0.08
    å¢ŀæĮģ
    -0.08
    èµŀ
    -0.08
    é«ĺåľ°
    -0.08
    縮
    -0.08
     Dok
    -0.08
    POSITIVE LOGITS
    éĢıè§Ĩ
    0.10
    å®īéĿĻ
    0.09
    è¦ģä¸įè¦ģ
    0.09
    ä¾ĥ
    0.09
    lew
    0.08
    严
    0.08
    kins
    0.08
    rix
    0.08
    rna
    0.08
    .PIPE
    0.08
    Activations Density 0.173%

    No Known Activations