© 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. 17109
    Prev
    Next
    INDEX
    Explanations

    introductions to lists of items

    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
    ogui
    -0.10
    åľ¨çº¿
    -0.10
    _MIC
    -0.09
    å¾Īåĸľæ¬¢
    -0.09
    å·¾
    -0.09
    æijĪ
    -0.08
    å²IJ
    -0.08
    åijĹ
    -0.08
    çľĩ
    -0.08
    utra
    -0.08
    POSITIVE LOGITS
    Enumerator
    0.10
    ç»Ħç»ĩå®ŀæĸ½
    0.09
    cef
    0.09
    ế
    0.09
    ä¸Ģè¡Į
    0.08
    èĨ¨
    0.08
    ijo
    0.08
    ä¿®åħ»
    0.08
    ä»įæľī
    0.08
    æīĭèĦļ
    0.08
    Activations Density 0.267%

    No Known Activations