© 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. 48555
    Prev
    Next
    INDEX
    Explanations

    sturdy, robust, durable construction

    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
    æĴĩ
    -0.10
    å¿Ĩ
    -0.09
    éľģ
    -0.08
    ãĤ¿ãĤ¤ãĥŁãĥ³ãĤ°
    -0.08
    人类
    -0.08
    å¾Ĺ天
    -0.08
    åĨħè¡£
    -0.08
    èĦ±ç¦»
    -0.08
    èݲ
    -0.08
    esto
    -0.08
    POSITIVE LOGITS
    èĢIJçĶ¨
    0.14
     sturdy
    0.13
     robust
    0.12
    æī¿åıĹ
    0.12
    åĿļåĽº
    0.12
    ç»ĵå®ŀ
    0.11
    稳åģ¥
    0.10
    çī¢åĽº
    0.10
     durability
    0.10
    çļĦè´¨éĩı
    0.10
    Activations Density 0.074%

    No Known Activations