© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20276
    Prev
    Next
    INDEX
    Explanations

    protecting from damage or entry

    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
    è¿Ł
    -0.11
    èµĤ
    -0.10
    鸩
    -0.09
    ç»ļ
    -0.09
    æĭ¿åĪ°
    -0.09
    è¿·
    -0.09
    ä¸įæĸŃçļĦ
    -0.09
     pressed
    -0.09
    è°Īè°Ī
    -0.09
    _locked
    -0.09
    POSITIVE LOGITS
    ibs
    0.09
    æĺ¯ä¸Ģ家
    0.09
    ÙģØ´
    0.09
    æķıæĦŁ
    0.09
    direct
    0.08
    å®ŀæĥł
    0.08
    amation
    0.08
    ç§Ģ
    0.08
    说å®ŀ
    0.08
    京津
    0.08
    Activations Density 0.153%

    No Known Activations