© 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. 56054
    Prev
    Next
    INDEX
    Explanations

    interrogative words

    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
    缸å½ĵ
    -0.10
     khá
    -0.10
    é¹Ħ
    -0.10
    åĸ½
    -0.09
    æľīåĪ©
    -0.09
    æĭ¨
    -0.09
     suscept
    -0.09
    åĮ®ä¹ı
    -0.09
    å¤ļæķ°
    -0.08
    ãģ¨ãģĦãģĨãģĵãģ¨ãģ§
    -0.08
    POSITIVE LOGITS
    æ·Ĩ
    0.11
    æĢİä¹ĪåĬŀ
    0.11
    æĥķ
    0.09
    åĽĽçº§
    0.08
    åijľ
    0.08
    irts
    0.08
    åŃ
    0.08
    æīŃ
    0.08
    éĻĮ
    0.08
    éĢīåĩº
    0.08
    Activations Density 0.042%

    No Known Activations