© 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. 53688
    Prev
    Next
    INDEX
    Explanations

    waste disposal

    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
    æ¼ı
    -0.10
    iola
    -0.09
    uft
    -0.09
     Hull
    -0.09
    空æ°Ķ
    -0.09
    åĪ»èĭ¦
    -0.08
    .pivot
    -0.08
    纲
    -0.08
    emarks
    -0.08
    kest
    -0.08
    POSITIVE LOGITS
    åºŁå¼ĥçī©
    0.09
    个å¤ļ
    0.09
    еÑĩа
    0.09
    åºŁ
    0.09
     laure
    0.08
    è¤Ĵ
    0.08
    ä¾Ŀæ³ķ追究
    0.08
    åºŁçī©
    0.08
    è±ĨèħIJ
    0.08
    å±±ä¸Ĭ
    0.08
    Activations Density 0.060%

    No Known Activations