© 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. 14509
    Prev
    Next
    INDEX
    Explanations

    STATE of

    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
    æ´»
    -0.20
    åIJĪçIJĨ
    -0.20
    æĭĶ
    -0.19
    oving
    -0.19
     книг
    -0.18
     Claude
    -0.18
    åįĸç»Ļ
    -0.18
    defaults
    -0.18
     ale
    -0.17
    ordon
    -0.17
    POSITIVE LOGITS
    айÑĤе
    0.20
    .disc
    0.18
    åľľ
    0.18
    éģĹçķĻ
    0.17
    å±Ģå±Ģéķ¿
    0.17
    à¹ģห
    0.17
    æ·±è¿ľ
    0.17
    é«ĺ空
    0.16
    æIJħæĭĮ
    0.16
    chaft
    0.16
    Activations Density 0.005%

    No Known Activations