© 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. 6388
    Prev
    Next
    INDEX
    Explanations

    quietly followed by action verbs

    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
    upe
    -0.09
    ãģĦãģĭ
    -0.08
    iations
    -0.08
    ç»·
    -0.08
    åģĩ
    -0.08
    ä¸įåĪĨ
    -0.08
    æĸ°å½¢åĬ¿ä¸ĭ
    -0.08
    çĥ
    -0.08
    unsch
    -0.08
    å®Įæķ´
    -0.08
    POSITIVE LOGITS
    æĤĦçĦ¶
    0.19
    æĤĦæĤĦ
    0.17
    æĤĦ
    0.14
    ä½İè°ĥ
    0.13
     quietly
    0.13
    æĹłå£°
    0.13
    ä¸įçŁ¥ä¸įè§ī
    0.11
    宣å¸ĥ
    0.10
     unnoticed
    0.10
    åģ·åģ·
    0.10
    Activations Density 0.042%

    No Known Activations