© 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. 11705
    Prev
    Next
    INDEX
    Explanations

    Tic Tac Toe, fall, Texas, Q:, exercise

    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
    çĻ»
    -0.23
    æĮ¯
    -0.21
    éĿ¢çĽ®
    -0.19
    群
    -0.19
    éĢı
    -0.19
     duty
    -0.19
    æµ·æĭĶ
    -0.19
    åĽ´
    -0.18
     thermo
    -0.18
    æĢİä¹ĪåĬŀ
    -0.18
    POSITIVE LOGITS
    éºĴ
    0.22
    èµĤ
    0.20
    æĹłæķ°æ¬¡
    0.20
    éĵĭ
    0.20
    éªĿ
    0.19
    èĪ
    0.19
     xét
    0.19
    ä¸įåİ»
    0.19
    éģ¿åħį
    0.19
    AVING
    0.18
    Activations Density 0.002%

    No Known Activations