© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8548
    Prev
    Next
    INDEX
    Explanations

    eyes, contact, locations

    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
    _BRANCH
    -0.10
    åŤ
    -0.09
    anonymous
    -0.09
    ãģ³
    -0.09
    anza
    -0.09
    æĭĪ
    -0.09
    åŁĭ
    -0.08
    å½ĵä¹ĭæĹłæĦ§
    -0.08
    èį£èªī
    -0.08
    _branch
    -0.08
    POSITIVE LOGITS
    å¾Īæ·±
    0.10
    çľ¼ç¥ŀ
    0.09
    wolf
    0.09
    xec
    0.09
    å¨ģæħij
    0.09
    建档
    0.09
    çıĪ
    0.08
    丼
    0.08
    isky
    0.08
     Hung
    0.08
    Activations Density 0.010%

    No Known Activations