© 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. 31414
    Prev
    Next
    INDEX
    Explanations

    expressing agreement or acknowledgment

    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
    ilos
    -0.10
    éľģ
    -0.08
    åįģä¹Ŀ大
    -0.08
    综åIJĪæĢ§
    -0.08
    讪
    -0.08
    bab
    -0.08
    _HE
    -0.08
     Ñģеб
    -0.08
    ãĤ¤ãĥĪ
    -0.08
    çľ¼åīįçļĦ
    -0.08
    POSITIVE LOGITS
    å°ıç¼ĸ
    0.12
    ç¬ĶèĢħ
    0.12
    æĪij们认为
    0.11
    çľĭæĿ¥
    0.11
    åıĪä¸Ģ次
    0.10
    æŃ¤ä¸¾
    0.09
    å°ıç¼ĸä¸Ģèµ·
    0.09
    对该
    0.09
    åIJ¬èµ·æĿ¥
    0.08
    ancel
    0.08
    Activations Density 0.177%

    No Known Activations