© 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. 13617
    Prev
    Next
    INDEX
    Explanations

    competitive grants and funding opportunities

    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
    çīºçī²
    -0.20
    coin
    -0.19
    antic
    -0.18
    éķ¿å¯¿
    -0.18
     Apt
    -0.18
    è´Ł
    -0.18
     grip
    -0.18
     bor
    -0.17
    .vocab
    -0.17
    FOUNDATION
    -0.17
    POSITIVE LOGITS
    çĶ³æĬ¥
    0.31
    çĶ³è¯·
    0.29
    é¼ĵåĬ±
    0.29
    æĬ¥éĢģ
    0.25
    è¦ģæ±Ĥ
    0.23
    çĶ³è«ĭ
    0.23
    å¡«æĬ¥
    0.23
    ä¸Ģç»ı
    0.22
    ç«ĭ项
    0.22
    çĶ¥
    0.21
    Activations Density 0.110%

    No Known Activations