© 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. 12029
    Prev
    Next
    INDEX
    Explanations

    at .org

    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
    ırl
    -0.19
    entr
    -0.19
    æĺ¼
    -0.19
    人æ°ijæľįåĬ¡
    -0.18
    åħļçļĦåįģ
    -0.18
    enton
    -0.18
    ora
    -0.18
    åħ¥é©»
    -0.17
    åĵ¡
    -0.17
    _APPEND
    -0.17
    POSITIVE LOGITS
    çĽijçĿ£æ£ĢæŁ¥
    0.18
    raj
    0.18
    HT
    0.18
    bled
    0.18
    ä¸ŃåĽ½åĪ¶éĢł
    0.17
    çļĦä»»åĬ¡
    0.17
    riage
    0.17
    åħŃåIJĪ
    0.17
    LT
    0.17
    isex
    0.17
    Activations Density 0.043%

    No Known Activations