© 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. 15944
    Prev
    Next
    INDEX
    Explanations

    mapping and tracing progress or journeys

    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
    éļ¶
    -0.22
    è¡ĮæĶ¿å¤Ħç½ļ
    -0.20
    ç¢į
    -0.18
    енд
    -0.18
    ë§IJ
    -0.17
    襻
    -0.17
    æĬĸ
    -0.17
    讲æķħäºĭ
    -0.17
    èѦæĥķ
    -0.17
    çī¹åĪ«æĺ¯åľ¨
    -0.17
    POSITIVE LOGITS
    æľĽåİ»
    0.20
    .Track
    0.19
    growth
    0.19
    éĢļå¾Ģ
    0.18
    åıijå±ķæĸ¹åIJij
    0.18
    åĩºåĩ»
    0.18
    æµģåIJij
    0.18
     relationships
    0.18
    æݨçIJĨ
    0.18
    ocracy
    0.18
    Activations Density 0.072%

    No Known Activations