© 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. 12816
    Prev
    Next
    INDEX
    Explanations

    learned something new

    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
    pch
    -0.22
    agra
    -0.21
    wel
    -0.21
    对çĿĢ
    -0.20
     Saga
    -0.20
    apel
    -0.19
    ä¸įåĨį
    -0.18
    usto
    -0.18
    è½®
    -0.18
    èµĦè´¨
    -0.18
    POSITIVE LOGITS
    æĶ¶èİ·
    0.42
    benef
    0.31
    åıĹçĽĬ
    0.30
    æĶ¶çĽĬ
    0.29
    æķĻè®Ń
    0.29
    outcome
    0.29
     benefit
    0.28
     outcome
    0.27
    åѦåĪ°
    0.27
    å¾ĹçĽĬ
    0.27
    Activations Density 0.146%

    No Known Activations