© 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. 14882
    Prev
    Next
    INDEX
    Explanations

    gold

    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
     Warp
    -0.19
    好åĿı
    -0.19
    ihan
    -0.18
    Wildcard
    -0.18
    éĨĭ
    -0.18
     Choice
    -0.17
    强åĬĽ
    -0.17
    èĬ¡
    -0.17
    è··
    -0.17
    iendo
    -0.16
    POSITIVE LOGITS
    çļĦæ¯Ķä¾ĭ
    0.21
    åĮ£
    0.20
    ç®Ķ
    0.20
    åħ®
    0.20
    æµģåħ¥
    0.20
    æ¯Ķä¾ĭ
    0.19
     literal
    0.19
     اÙĦخاÙħ
    0.18
    禧
    0.18
     gold
    0.18
    Activations Density 0.010%

    No Known Activations