© 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. 22079
    Prev
    Next
    INDEX
    Explanations

    in + noun

    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
    é¹ŀ
    -0.09
    åĨľåľº
    -0.09
    ugi
    -0.09
    andro
    -0.08
    JNIEnv
    -0.08
    ilan
    -0.08
    ä¸Ģ个å°ı
    -0.08
    骥
    -0.08
    èµĮåľº
    -0.08
    езÑĥлÑĮÑĤ
    -0.08
    POSITIVE LOGITS
    ä¹Łæĺ¯å¾Ī
    0.10
    intr
    0.09
    宿
    0.09
    é£İ鼨
    0.09
    纵深
    0.08
     terms
    0.08
    è¿Ļæĸ¹éĿ¢
    0.08
    æģ¤
    0.08
    inator
    0.08
    çĽ¸å¯¹è¾ĥ
    0.08
    Activations Density 0.060%

    No Known Activations