© 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. 14955
    Prev
    Next
    INDEX
    Explanations

    arrives, comes, entered, or approaches

    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
    references
    -0.20
    éĤ£ç§į
    -0.19
    建çŃijå·¥ç¨ĭ
    -0.18
    黼
    -0.18
    çĻĥ
    -0.18
    loser
    -0.18
    å°¼åħĭ
    -0.17
    å¾Īæĥ³
    -0.17
    åIJİéĿ¢çļĦ
    -0.17
    _Common
    -0.17
    POSITIVE LOGITS
    è¿ĩæĿ¥
    0.25
    è¿ĽæĿ¥
    0.23
    æĿ¥
    0.22
    强åĬ¿
    0.21
    åĪ°æĿ¥
    0.20
    帮å¿Ļ
    0.20
    åijĬ
    0.20
    åħ¥
    0.19
    æĿ¥è¿Ľè¡Į
    0.19
    åīįæĿ¥
    0.18
    Activations Density 0.050%

    No Known Activations