© 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. 11883
    Prev
    Next
    INDEX
    Explanations

    website suffixes or paths

    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
    emd
    -0.21
    mina
    -0.20
     SND
    -0.19
    追究
    -0.19
    éĨ¢
    -0.19
    Ban
    -0.18
    arias
    -0.18
    _BROWSER
    -0.18
    oom
    -0.18
     intentions
    -0.18
    POSITIVE LOGITS
    çī¹å®ļ
    0.25
     especÃŃfica
    0.21
    æĺİ亮
    0.20
    奢ä¾Ī
    0.19
    åħīèĬĴ
    0.19
    èĮ«èĮ«
    0.19
     specific
    0.19
    çĮľ
    0.18
    毫æĹłçĸij
    0.18
    -fixed
    0.18
    Activations Density 0.039%

    No Known Activations