© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37512
    Prev
    Next
    INDEX
    Explanations

    inherited

    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
    ÑĢай
    -0.10
    ä¸Ģå¤ľ
    -0.10
    niejs
    -0.10
    èıŁ
    -0.10
    é»Ħæĺı
    -0.09
    onn
    -0.09
    elho
    -0.09
    -eyed
    -0.09
    ç«ŀèµĽ
    -0.09
    Ñģл
    -0.09
    POSITIVE LOGITS
    åºĸ
    0.11
    chaft
    0.09
    åĵij
    0.09
    åħĪæĺ¯
    0.09
    UTES
    0.08
    ä¸ĭæĿ¥çļĦ
    0.08
    OrUpdate
    0.08
    loom
    0.08
    è¯¥é¡¹çĽ®
    0.08
    éĶ´
    0.08
    Activations Density 0.038%

    No Known Activations