© 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. 15366
    Prev
    Next
    INDEX
    Explanations

    Alien, Story, Man, code, Create

    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
    å¸ĤæĶ¿
    -0.21
    ately
    -0.19
    avit
    -0.19
    æijĩäºĨ
    -0.18
    _ABI
    -0.17
    urator
    -0.17
    ä¼Ľ
    -0.17
    碼
    -0.17
     insulting
    -0.17
    rollable
    -0.17
    POSITIVE LOGITS
    æĿĥå¨ģ
    0.21
     chù
    0.21
    æľĢ好
    0.20
    ä»ħä¾ĽåıĤèĢĥ
    0.20
    åĿIJ
    0.20
    æĺ¯æľĢ好çļĦ
    0.20
    æł¸åĩĨ
    0.20
    çıłæ±Ł
    0.20
    æĪijæīį
    0.20
     COPYRIGHT
    0.19
    Activations Density 0.001%

    No Known Activations