© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51283
    Prev
    Next
    INDEX
    Explanations

    outgunned or outnumbered

    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
    èİ«
    -0.09
    æĿĵ
    -0.09
    ukt
    -0.09
    OUS
    -0.09
    .§
    -0.09
    å¸ĪåħĦ
    -0.08
    elson
    -0.08
    å²ģ以ä¸ĭ
    -0.08
    changer
    -0.08
    ystack
    -0.08
    POSITIVE LOGITS
    äºĨå¤ļå°ij
    0.10
    人家
    0.10
    äºĨæĪijçļĦ
    0.09
    MER
    0.09
    è¿ij两年
    0.09
     mer
    0.08
    è¿Ļ两年
    0.08
    诺
    0.08
    çĴĢçĴ¨
    0.08
    åı£å¾Ħ
    0.08
    Activations Density 0.003%

    No Known Activations