© 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. 10943
    Prev
    Next
    INDEX
    Explanations

    life expectancy and its discussion

    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
    çī¹æľĹ
    -0.23
    .phase
    -0.21
    makt
    -0.21
    âīĤ
    -0.19
    大æĪĺ
    -0.19
    åĭŁéĽĨèµĦéĩij
    -0.19
    ç³ķ
    -0.18
    éĤij
    -0.18
    é©°
    -0.18
     kick
    -0.18
    POSITIVE LOGITS
    寿åij½
    0.22
    çĶ·å¥³
    0.21
    éķ¿å¯¿
    0.21
    壽
    0.19
    丧
    0.19
     Murder
    0.19
    life
    0.19
    寿
    0.18
    è¡°èĢģ
    0.18
    ç±
    0.18
    Activations Density 0.016%

    No Known Activations