© 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. 54139
    Prev
    Next
    INDEX
    Explanations

    numbers in lists

    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
     decor
    -0.09
    让ä»ĸ们
    -0.09
    综åIJĪæĢ§
    -0.09
    аÑĢÑĮ
    -0.08
    oud
    -0.08
    ãģ§ãģĻãĤĪ
    -0.08
    aram
    -0.08
    ä¹ĭä½ľ
    -0.08
    ÑĢаж
    -0.08
    aji
    -0.08
    POSITIVE LOGITS
    ä½¾
    0.09
    è¯Ħæµĭ
    0.09
    lite
    0.08
    å¸ĤæķĻèĤ²
    0.08
    WISE
    0.08
    Backing
    0.08
    绵
    0.08
    å¯Ħ
    0.08
    rev
    0.08
    legend
    0.08
    Activations Density 0.065%

    No Known Activations