© 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. 18584
    Prev
    Next
    INDEX
    Explanations

    contrast or exception

    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±ħ室
    -0.10
    oley
    -0.09
    è¯Ī
    -0.09
    æĹ¥åĨħ
    -0.09
    åħ¶æ¬¡æĺ¯
    -0.08
     Cook
    -0.08
     Ober
    -0.08
    æķ£
    -0.08
    ä¹Łä¸įæĺ¯
    -0.08
    è¤ĵ
    -0.08
    POSITIVE LOGITS
    åīįæıIJæĺ¯
    0.13
    åīįæıIJ
    0.11
    æľĢ好
    0.10
    andi
    0.10
    é¡»
    0.09
    stantiate
    0.09
    ä¼ļæľī
    0.09
    ãĤĦãĤĬ
    0.09
    è¦ģçľĭ
    0.09
    à°³
    0.09
    Activations Density 0.075%

    No Known Activations