© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12596
    Prev
    Next
    INDEX
    Explanations

    winning or losing outcomes in games

    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
    éĨ®
    -0.20
    秦
    -0.18
    åĹ·
    -0.18
    å¼ĢçĿĢ
    -0.18
    arde
    -0.18
    è§ģéĿ¢
    -0.18
     sclerosis
    -0.17
    lesia
    -0.17
     pertinent
    -0.17
    éĤ£ç§į
    -0.17
    POSITIVE LOGITS
    å¼ķ导
    0.23
    èĪ¸
    0.20
    arnings
    0.20
    Dal
    0.19
    ãĤ°ãĥ«
    0.19
    æī¿è®¤
    0.18
    ç»ĵå±Ģ
    0.18
    çīĽ
    0.18
    æĢĽ
    0.18
     Finish
    0.18
    Activations Density 0.015%

    No Known Activations