© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20080
    Prev
    Next
    INDEX
    Explanations

    dealing with business or interactions

    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
    çłŃ
    -0.10
    鸳
    -0.10
    ä¸ĩ家
    -0.09
    elig
    -0.09
    åĪ¶éĢł
    -0.09
    ige
    -0.09
    é¹Ĺ
    -0.09
    elight
    -0.08
    DataReader
    -0.08
    çĨĦ
    -0.08
    POSITIVE LOGITS
    æīĵ交éģĵ
    0.24
    æݥ触
    0.16
    交å¾Ģ
    0.14
     dealings
    0.13
    交äºĴ
    0.13
    对æİ¥
    0.12
    æ´½è°Ī
    0.12
    æ´½
    0.12
    Interaction
    0.12
     interaction
    0.12
    Activations Density 0.060%

    No Known Activations