© 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. 20887
    Prev
    Next
    INDEX
    Explanations

    Dj, z, ch, dz

    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
    æIJº
    -0.09
    indow
    -0.08
    apid
    -0.08
     Fle
    -0.08
    审计
    -0.08
    çļĩåĨł
    -0.08
    飶
    -0.08
    ä½ľæĸĩ
    -0.08
    _ATTRIB
    -0.08
     vos
    -0.07
    POSITIVE LOGITS
    èĩªåĬ¨
    0.11
    èĻij
    0.10
    è£ģå®ļ
    0.09
    èĩªåĭķ
    0.09
    主ä¹īèĢħ
    0.09
    amd
    0.09
    èĢĮæĿ¥
    0.09
    èĭŀ
    0.09
    è£ģ
    0.09
    æ¯Ļ
    0.08
    Activations Density 0.109%

    No Known Activations