© 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. 48578
    Prev
    Next
    INDEX
    Explanations

    engine ignition timing

    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
    沿线
    -0.10
    æµĨ
    -0.09
    omed
    -0.08
    umbo
    -0.08
    缴åįĩæľº
    -0.08
    ç´«èī²
    -0.08
    thouse
    -0.08
     Elli
    -0.08
    å·¨åŀĭ
    -0.08
    åıįåĩ»
    -0.08
    POSITIVE LOGITS
    æ¦ķ
    0.11
    åıijåĬ¨æľº
    0.11
    å¼ķæĵİ
    0.10
     unle
    0.10
    åıĤ
    0.10
    汽油
    0.09
    ×ľ×ª
    0.09
    çĩĥçĥ§
    0.09
    åIJĮèĥŀ
    0.09
    à¸Ńà¸Ń
    0.09
    Activations Density 0.091%

    No Known Activations