© 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. 12714
    Prev
    Next
    INDEX
    Explanations

    dog and pets

    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
    温æļĸ
    -0.24
    åħīè¾ī
    -0.24
    åįĩ温
    -0.22
    åħīèĬĴ
    -0.21
    FullPath
    -0.19
    Ø®
    -0.19
    åĨħéĥ¨
    -0.19
    çĤĴ
    -0.18
    æĺİ亮
    -0.18
    å¾Ģä¸Ĭ
    -0.18
    POSITIVE LOGITS
    çݯå¢ĥåį«çĶŁ
    0.24
    饲åħ»
    0.23
    æ´Ļ
    0.21
    åħ¬åĽŃ
    0.21
    è¦ĨçĽĸçİĩ
    0.21
    nement
    0.20
    æݬ
    0.20
    agal
    0.20
    çĬ¬
    0.19
    åħį
    0.19
    Activations Density 0.013%

    No Known Activations