© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1497
    Prev
    Next
    INDEX
    Explanations

    known to

    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
    å®ŀè´¨
    -0.26
    æĥ³è±¡
    -0.26
    羣æĺ¯
    -0.24
    以为
    -0.23
    羣æŃ£
    -0.23
     vraiment
    -0.23
     truly
    -0.23
    ä¼¼
    -0.22
    å®ŀè´¨æĢ§
    -0.22
    è¯Ŀè¯ŃæĿĥ
    -0.22
    POSITIVE LOGITS
    ledge
    0.26
    OPS
    0.25
     known
    0.25
    chy
    0.24
     documented
    0.24
    anced
    0.24
    -known
    0.24
    æľīè¿Ļæł·çļĦ
    0.23
    facts
    0.23
    å¤ļãģĦ
    0.23
    Activations Density 0.159%

    No Known Activations