© 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. 35923
    Prev
    Next
    INDEX
    Explanations

    one that

    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
    çıĪ
    -0.09
    çijĽ
    -0.09
    croft
    -0.09
    çIJ¨
    -0.09
    äºĨä¸Ģä¸ĭ
    -0.09
    chter
    -0.09
    å°±æĺ¯è¿Ļæł·
    -0.08
    allback
    -0.08
    大æĪ·
    -0.08
    é³ĸ
    -0.08
    POSITIVE LOGITS
    èĥ½åľ¨
    0.09
    èµĸ以
    0.09
    uario
    0.09
    ä¸įåĪĨ
    0.09
    ONES
    0.08
    ayers
    0.08
    èĥ½è®©
    0.08
    天天
    0.08
    çıł
    0.08
    geist
    0.08
    Activations Density 0.059%

    No Known Activations