© 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. 52363
    Prev
    Next
    INDEX
    Explanations

    win against

    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
    å±ĬæŶ
    -0.08
    zan
    -0.08
    æŃ£å½ĵ
    -0.08
    æŶ任
    -0.08
    rum
    -0.08
    èĭ¥æľī
    -0.08
    Caught
    -0.08
    riba
    -0.08
    dock
    -0.08
    _indent
    -0.08
    POSITIVE LOGITS
    åıĪä¸Ģ次
    0.11
    åĤįæĻļ
    0.11
    ä¸Ģåľº
    0.11
    å®ĺæĸ¹å¾®åįļ
    0.10
    æĺ¨æĻļ
    0.10
    æ»Ķ
    0.10
    å¾Īé«ĺåħ´
    0.09
    æĶ¶èİ·
    0.09
    äºĨä¸Ģåľº
    0.09
     heap
    0.09
    Activations Density 0.145%

    No Known Activations