© 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. 16054
    Prev
    Next
    INDEX
    Explanations

    impose tariffs or penalties

    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
    åı¯éĿłçļĦ
    -0.20
    istics
    -0.19
    åı¯éĿł
    -0.17
    inet
    -0.17
    尽头
    -0.17
    mma
    -0.16
    åħĴ
    -0.15
    é³ı
    -0.15
    pdo
    -0.15
    ouse
    -0.15
    POSITIVE LOGITS
    ments
    0.21
    inging
    0.20
     عÙĦÙĬÙĩÙħ
    0.18
     upon
    0.18
    ément
    0.17
    ively
    0.17
     عÙĦÙĬÙĥ
    0.17
    ì°©
    0.16
    LEY
    0.16
     penalties
    0.16
    Activations Density 0.012%

    No Known Activations