© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12417
    Prev
    Next
    INDEX
    Explanations

    pokémon games

    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
    è§Ħ模åĮĸ
    -0.20
    æµĨ
    -0.20
    æĬĢ
    -0.19
    åĺ´
    -0.19
    æºĩ
    -0.19
    eri
    -0.19
    禹
    -0.19
    椽
    -0.18
    _drv
    -0.18
    дж
    -0.18
    POSITIVE LOGITS
     Dalton
    0.21
    çĤ¼
    0.21
    agged
    0.20
    çīĪ
    0.19
    ä¸Ģä¸Ŀ
    0.18
    çĶ·çĶŁ
    0.18
    agger
    0.18
    çĭĦ
    0.18
    symbols
    0.18
    ç°ª
    0.17
    Activations Density 0.006%

    No Known Activations