© 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. 49221
    Prev
    Next
    INDEX
    Explanations

    year ended

    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
    æ¯ı天éĥ½
    -0.10
    宿
    -0.09
    æĭį
    -0.08
    æĮ½
    -0.08
    ner
    -0.08
    ä¸İæŶ
    -0.08
    DataTable
    -0.08
    æĦŁäºº
    -0.08
    -ch
    -0.08
    çĿ«
    -0.08
    POSITIVE LOGITS
    ä»Ĺ
    0.10
    ç»Ī究
    0.09
     Prescott
    0.09
    oked
    0.09
    éľŃ
    0.09
    æĬĬè¿Ļ个
    0.08
    unsch
    0.08
    éĤĭ
    0.08
    ิà¸ĩ
    0.08
    åIJĮèĥŀ
    0.08
    Activations Density 0.017%

    No Known Activations