© 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. 11682
    Prev
    Next
    INDEX
    Explanations

    air defense and missile systems

    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
    abol
    -0.23
    æµģåĬ¨
    -0.20
    ðŁĵĮ
    -0.20
    ç³Ĭ
    -0.20
     Flood
    -0.20
    å¼Ģåıij建设
    -0.19
     SWAT
    -0.19
    éĿ¢åħ·
    -0.19
    dsl
    -0.19
    veau
    -0.19
    POSITIVE LOGITS
    éĽ·è¾¾
    0.28
    éĺ²åį«
    0.26
    å¨ģèĥģ
    0.26
    æķĮ
    0.25
    èĩªèº«
    0.22
     radar
    0.22
    éĺ²å¾¡
    0.22
     hostile
    0.21
    æįķæįī
    0.20
    继
    0.20
    Activations Density 0.033%

    No Known Activations