© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22039
    Prev
    Next
    INDEX
    Explanations

    websites and sites

    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
    _MOV
    -0.10
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.09
    æĺ¼
    -0.09
    cept
    -0.09
    strap
    -0.09
    uba
    -0.09
    æĪIJç«ĭ以æĿ¥
    -0.08
     desn
    -0.08
    reon
    -0.08
     playoff
    -0.08
    POSITIVE LOGITS
    ullet
    0.11
    zin
    0.10
    æĬ¤æłı
    0.09
    mdi
    0.08
     Meyer
    0.08
    icity
    0.08
    åĢ¼å¾Ĺä¸Ģ
    0.08
    åĵĻ
    0.08
    è¿Ļæīį
    0.08
     veil
    0.08
    Activations Density 0.018%

    No Known Activations