© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8247
    Prev
    Next
    INDEX
    Explanations

    its/their + noun

    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
    erna
    -0.10
    她们
    -0.10
    .nih
    -0.10
    æ¼Ĥ亮çļĦ
    -0.09
    æľīæīĢ
    -0.09
     Sent
    -0.08
    _esc
    -0.08
    è´«ç©·
    -0.08
    egl
    -0.08
    å°Ĩ以
    -0.08
    POSITIVE LOGITS
    /or
    0.10
     ilk
    0.09
    rew
    0.09
     associated
    0.09
    пп
    0.08
    panse
    0.08
     оÑĦоÑĢмлен
    0.08
    åIJ¯è¿ª
    0.08
    pler
    0.08
    对æīĭ
    0.08
    Activations Density 0.051%

    No Known Activations