© 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. 16539
    Prev
    Next
    INDEX
    Explanations

    financial matters, loans, eligibility, IR, gems

    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
    ess
    -0.19
    fold
    -0.19
    ãģ¦ãģĦ
    -0.19
    esson
    -0.19
    å¯Ĥ
    -0.18
    ires
    -0.18
    pon
    -0.18
    icont
    -0.18
    yz
    -0.17
     sticky
    -0.17
    POSITIVE LOGITS
    ä¸ĵåijĺ
    0.21
    åĪ¶åº¦æĶ¹éĿ©
    0.21
    åIJįé¢Ŀ
    0.20
    _FD
    0.20
    缸åħ³æĶ¿çŃĸ
    0.20
    èµĦéĩij
    0.20
    å¡«æĬ¥
    0.19
    æľīèī²
    0.19
    迤
    0.19
    åŁºéĩij
    0.19
    Activations Density 0.003%

    No Known Activations