© 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. 1131
    Prev
    Next
    INDEX
    Explanations

    melting and temperature changes

    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
    æ·¹
    -0.30
    .Raw
    -0.24
    è¾Ĺ
    -0.24
    èĮĨ
    -0.24
    unda
    -0.23
     raw
    -0.23
    æŀĦ建
    -0.23
    grave
    -0.23
    æĮ½åĽŀ
    -0.23
    ç£IJ
    -0.23
    POSITIVE LOGITS
    éĢĤ度
    0.30
    æļĸ
    0.29
    ä½ĵ温
    0.28
     warming
    0.28
     warmer
    0.27
    温æļĸ
    0.27
     warmed
    0.26
    Ļ¨
    0.26
    éĻį温
    0.26
    temperature
    0.25
    Activations Density 0.009%

    No Known Activations