© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10823
    Prev
    Next
    INDEX
    Explanations

    head coverings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    çĩĥæ²¹
    -0.23
    è·º
    -0.22
    æµģ产
    -0.21
    æĸĻçIJĨ
    -0.20
     fuel
    -0.20
    æİĴ骨
    -0.20
    大å§IJ
    -0.19
    ç¼İ
    -0.19
    å¿ĥåĬ¨
    -0.19
    èº
    -0.19
    POSITIVE LOGITS
    头
    0.38
    é¢ħ
    0.35
     head
    0.34
    头éĥ¨
    0.34
    çľ¼éķľ
    0.34
    æĪ´
    0.34
    èĦijè¢ĭ
    0.33
    头顶
    0.33
    éłŃ
    0.33
     Head
    0.32
    Activations Density 0.210%

    No Known Activations