© 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. 10866
    Prev
    Next
    INDEX
    Explanations

    memory and forgetting

    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
    ä¹ĭéģĵ
    -0.22
    ç²®
    -0.20
    髯
    -0.20
    èĩĬ
    -0.20
    éĤ£ä¹Īç®Ģåįķ
    -0.19
    çŀ»
    -0.19
    éħ°
    -0.18
     Spread
    -0.18
    è¿Łè¿Ł
    -0.18
    ä½ĵçİ°åľ¨
    -0.18
    POSITIVE LOGITS
    è¿Ļ段
    0.26
    éĩįéĩį
    0.20
    åħ·ä½ĵåĨħ容
    0.20
    åİŁåĽł
    0.20
    ergency
    0.20
    ç´Ĭ
    0.20
     details
    0.19
     forgot
    0.19
    èĩªå·±
    0.19
    åīįä¸ĸ
    0.19
    Activations Density 0.009%

    No Known Activations