© 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. 14439
    Prev
    Next
    INDEX
    Explanations

    solving puzzles, bypass, radiation exposure, reproduction, call graphs, data moving

    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
    åģ¶
    -0.22
     Hind
    -0.19
     slower
    -0.19
    sw
    -0.19
    ido
    -0.19
    SessionFactory
    -0.19
    worth
    -0.18
    wish
    -0.18
    wave
    -0.17
    æĦŁåĬ¨
    -0.17
    POSITIVE LOGITS
     involved
    0.24
    æīĵ交éģĵ
    0.23
    çıħ
    0.22
    ä¸ĢéŨ
    0.21
     during
    0.21
    éĹ´æİ¥
    0.21
    .isRequired
    0.20
    éĴ»
    0.20
    å¿Ļ
    0.20
     incidental
    0.20
    Activations Density 0.393%

    No Known Activations