© 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. 30983
    Prev
    Next
    INDEX
    Explanations

    happiness and agreement

    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
    ë³¼
    -0.09
    è¯ķ
    -0.08
    ÙħÙī
    -0.08
    monds
    -0.08
    ì¿ł
    -0.08
    彩èī²
    -0.08
    ä¸įèĩ³äºİ
    -0.08
    UBE
    -0.08
     collapsing
    -0.08
    彬
    -0.08
    POSITIVE LOGITS
     nor
    0.10
    èĢĮæĺ¯
    0.10
    娣
    0.10
    nor
    0.10
    好çľĭ
    0.10
    éªIJ
    0.09
    æ³ģ
    0.09
    ä¹Łä¸įæĥ³
    0.09
    çļĦç¡®
    0.09
    ç¿Ĵæħ£
    0.09
    Activations Density 0.031%

    No Known Activations