© 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. 63597
    Prev
    Next
    INDEX
    Explanations

    networking concepts

    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
    æĽ´æ·±
    -0.11
    orest
    -0.11
    å¨ĺ
    -0.10
    æ°Ķæģ¯
    -0.10
    çľ·
    -0.10
    _dn
    -0.10
    ç´§å¼ł
    -0.10
    ecycle
    -0.09
     sat
    -0.09
    å¯Ŀ
    -0.09
    POSITIVE LOGITS
    LAG
    0.10
     ìĦľ
    0.09
    lag
    0.09
     online
    0.09
    è¶Ĭ
    0.09
     ONLINE
    0.09
    ä¸ĩåı°
    0.08
    天ä¸Ĭ
    0.08
    åľ¨çº¿
    0.08
     server
    0.08
    Activations Density 0.119%

    No Known Activations