© 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. 27572
    Prev
    Next
    INDEX
    Explanations

    well, 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
    ä¹İ
    -0.09
    è¯
    -0.09
    èĦī
    -0.08
    èĦĪ
    -0.08
    ?,?,
    -0.08
    âĦħ
    -0.08
    åĴ½åĸī
    -0.08
     Burton
    -0.08
    ãĤ¥
    -0.08
    æĸ°èĤ¡
    -0.07
    POSITIVE LOGITS
    GRA
    0.09
    ÑĢоÑĪ
    0.09
    olvers
    0.09
    çIJ¼
    0.09
    èµ·çłģ
    0.09
    ä»Ĭ天æĪij们
    0.08
    ä¸Ĭåİ»
    0.08
     tradition
    0.08
    uten
    0.08
    ollection
    0.08
    Activations Density 0.050%

    No Known Activations