© 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. 16884
    Prev
    Next
    INDEX
    Explanations

    McCormack

    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
    åı¯æĥ³
    -0.09
     ведÑĮ
    -0.09
    immutable
    -0.08
    egot
    -0.08
    probe
    -0.08
    otation
    -0.08
    rim
    -0.08
    举æĬ¥çĶµè¯Ŀ
    -0.08
    ordial
    -0.08
    ails
    -0.08
    POSITIVE LOGITS
    tran
    0.10
    agan
    0.10
     воÑĤ
    0.09
    åĬŀåħ¬åİħ
    0.09
    å·¥ä½ľçļĦ
    0.09
    å¸ľ
    0.08
    æ²ģ
    0.08
    sons
    0.08
    uhan
    0.08
    çĶŁæ´»æĸ¹å¼ı
    0.08
    Activations Density 0.012%

    No Known Activations