© 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. 6379
    Prev
    Next
    INDEX
    Explanations

    establish/establishing

    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
    é¢Ł
    -0.09
    ConfigurationException
    -0.09
    รวà¸ļ
    -0.09
    åĽ¿
    -0.09
    .hd
    -0.09
     naken
    -0.09
     ADVISED
    -0.09
    è¿ĩçļĦ
    -0.09
    꺼
    -0.09
    inoa
    -0.09
    POSITIVE LOGITS
    åŁºè°ĥ
    0.13
     establish
    0.11
    æĸ°æł¼å±Ģ
    0.10
    æĪIJç«ĭäºĨ
    0.09
     Establish
    0.09
     priorities
    0.09
    7
    0.09
    1
    0.09
    xis
    0.09
     establishing
    0.09
    Activations Density 0.080%

    No Known Activations