© 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. 16315
    Prev
    Next
    INDEX
    Explanations

    protecting privacy/information

    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
    æIJł
    -0.19
    çļĦåĬŀæ³ķ
    -0.19
    çĶ¨åľ°
    -0.18
    æŀľæĸŃ
    -0.18
    èħ¹
    -0.18
    åŃķèĤ²
    -0.18
    ç²¹
    -0.18
    CLAIM
    -0.18
    æĭ¥æĬ±
    -0.18
    éĿ¢è²Į
    -0.18
    POSITIVE LOGITS
     Drill
    0.23
    å·¥ä½ľäººåijĺ
    0.21
    æľªæĪIJå¹´
    0.20
    å¾®åįļ
    0.20
    æİ¥åıĹéĩĩ访
    0.20
    nds
    0.19
    esy
    0.19
    ingo
    0.19
    åħ·ä½ĵåĨħ容
    0.19
     Woo
    0.19
    Activations Density 0.017%

    No Known Activations