© 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. 2167
    Prev
    Next
    INDEX
    Explanations

    Tim Burton, Jones, Rudolph, Intelligent Team

    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
    bles
    -0.32
    ä¹īåĬ¡
    -0.24
     Lost
    -0.23
     setStatus
    -0.23
    ettle
    -0.22
    itution
    -0.22
    ä¸įä½ı
    -0.22
    æŀª
    -0.22
     status
    -0.21
    _Free
    -0.21
    POSITIVE LOGITS
     pumps
    0.26
    æĸ°åŁİ
    0.24
     Mahar
    0.24
    é¼»åŃIJ
    0.22
    boards
    0.22
    cov
    0.22
    signature
    0.22
    æĵ¤
    0.22
    screen
    0.22
    æĬ¥ä¸ļ
    0.22
    Activations Density 0.002%

    No Known Activations