© 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. 11378
    Prev
    Next
    INDEX
    Explanations

    big/major/huge + concept

    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
    ä¸Ģæīĭ
    -0.08
    apl
    -0.08
    以
    -0.08
    amodel
    -0.08
     оÑĤмеÑĤиÑĤÑĮ
    -0.08
    ansk
    -0.08
    æľĶ
    -0.08
    mant
    -0.08
     Nim
    -0.08
    å¦Ļ
    -0.08
    POSITIVE LOGITS
    ä¸įå°ı
    0.12
    ä¸įå°ıçļĦ
    0.11
    åĬłåĪĨ
    0.10
    éļIJå½¢
    0.09
    ä¸įçŁ¥ä¸įè§ī
    0.09
    Ùħرا
    0.09
    stro
    0.09
     underst
    0.09
    æ¸į
    0.09
    æĴŀ
    0.09
    Activations Density 0.041%

    No Known Activations