© 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. 16904
    Prev
    Next
    INDEX
    Explanations

    sauce and condiments

    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
    绪
    -0.25
    梦è§ģ
    -0.20
    .xy
    -0.20
    æIJºå¸¦
    -0.19
     Bout
    -0.19
    è¿Ŀ
    -0.19
    家纺
    -0.19
    常è¯Ĩ
    -0.19
    å¾ģä¿¡
    -0.19
    æĥ°
    -0.18
    POSITIVE LOGITS
    éħ±
    0.22
    åı£åij³
    0.21
    rible
    0.20
     sauce
    0.20
    ric
    0.20
     Tigers
    0.18
     Sick
    0.18
    çĥ§çĥ¤
    0.18
    _rc
    0.18
    诱人
    0.18
    Activations Density 0.006%

    No Known Activations