© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 802
    Prev
    Next
    INDEX
    Explanations

    Division, Part, Parte

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    į°
    -0.23
    .books
    -0.22
    读åIJİ
    -0.22
    çīŁ
    -0.22
    mast
    -0.22
    edition
    -0.22
    æł·å¼ı
    -0.22
     Staten
    -0.22
    _BLOCKS
    -0.21
    forge
    -0.21
    POSITIVE LOGITS
    PERT
    0.25
    ä¸¥æł¼çļĦ
    0.24
    геÑĢ
    0.24
    æ°´éĩı
    0.23
    æĤĸ
    0.23
     XK
    0.22
    弦
    0.22
     pige
    0.22
    PCA
    0.21
     pigeon
    0.21
    Activations Density 0.002%

    No Known Activations