© 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. 6592
    Prev
    Next
    INDEX
    Explanations

    features a noun phrase or clause

    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
    åĮ¡
    -0.11
    æĺİçĻ½äºĨ
    -0.10
    aryl
    -0.09
    å¥ı
    -0.09
    leans
    -0.09
    å®ĥ们
    -0.09
    æİĢèµ·
    -0.09
    æijĪ
    -0.09
    令çīĮ
    -0.08
    è¿Ļä¹Ī说
    -0.08
    POSITIVE LOGITS
    éĿŀ常å¤ļçļĦ
    0.09
     a
    0.09
    ä¸ī项
    0.08
    ãģŁãģı
    0.08
    uate
    0.08
    “
    0.08
    erate
    0.08
    èĭĩ
    0.08
     several
    0.07
    ned
    0.07
    Activations Density 0.086%

    No Known Activations