© 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. 51966
    Prev
    Next
    INDEX
    Explanations

    interface declarations and constraints

    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
     dirt
    -0.08
    士
    -0.08
    åĭŁ
    -0.08
     tall
    -0.08
     Jar
    -0.08
    ä¸įçͱå¾Ĺ
    -0.08
    注å®ļ
    -0.08
    å¯ĮåĬĽ
    -0.08
    åįİå°Ķ
    -0.08
     coll
    -0.08
    POSITIVE LOGITS
    ãĤ¤ãĥ³ãĤ¿ãĥ¼ãĥ
    0.12
    çķĮéĿ¢
    0.10
    æľªçŁ¥
    0.10
    åIJĮ缣
    0.09
    /interface
    0.09
    çļ®
    0.09
    DataExchange
    0.09
     Interfaces
    0.09
    飬
    0.08
     Whale
    0.08
    Activations Density 0.351%

    No Known Activations