© 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. 15947
    Prev
    Next
    INDEX
    Explanations

    active duty or service

    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
    éĤij
    -0.21
    èĩªæĿ¥
    -0.19
    RY
    -0.19
    缺åı£
    -0.19
    iac
    -0.18
    åħĪ导
    -0.18
    .utf
    -0.18
    çį¾
    -0.17
    åĹī
    -0.17
    å¾ĹæĦı
    -0.17
    POSITIVE LOGITS
    çĬ¶æĢģä¸ĭ
    0.23
    æľŁ
    0.23
    å¹´éĻIJ
    0.21
     status
    0.19
    /non
    0.19
    åįĹæµ·
    0.19
    .CG
    0.19
    çĬ¶æĢģ
    0.19
    æĭ¼æIJı
    0.19
    åħ¢
    0.18
    Activations Density 0.004%

    No Known Activations