© 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. 47809
    Prev
    Next
    INDEX
    Explanations

    smartphone, motorcycle, handset, bike, phone, sedan, tank

    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
    æĺ¯ä¸ĢåIJį
    -0.09
    rede
    -0.09
    轶
    -0.09
    çĸı
    -0.08
    uding
    -0.08
    æĥľ
    -0.08
    楼ä¸Ĭ
    -0.08
    å°ĸ
    -0.08
    æįº
    -0.08
    asper
    -0.08
    POSITIVE LOGITS
    巨头
    0.11
    è¾IJ
    0.10
    æ·ĸ
    0.09
    è¯Ī
    0.08
     Ner
    0.08
    rying
    0.08
    eries
    0.08
     Armed
    0.08
    çŀij
    0.08
    _READY
    0.08
    Activations Density 0.259%

    No Known Activations