© 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. 16027
    Prev
    Next
    INDEX
    Explanations

    media and communication channels

    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
    kos
    -0.20
    .Parser
    -0.19
    /g
    -0.19
    æĹºåŃ£
    -0.18
     Process
    -0.18
    çļĦ大
    -0.18
    çIJħ
    -0.18
    apo
    -0.18
    logged
    -0.18
    åİĨç¨ĭ
    -0.17
    POSITIVE LOGITS
    å½¢å¼ı
    0.41
    è½½ä½ĵ
    0.36
    æīĭ段
    0.33
    æĸ¹å¼ı
    0.28
    å¤ļæł·
    0.27
    çŃīå½¢å¼ı
    0.27
    åªĴä»ĭ
    0.26
     forms
    0.26
     ÑĦоÑĢме
    0.26
    å¤ļç§įå½¢å¼ı
    0.26
    Activations Density 0.078%

    No Known Activations