© 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. 13477
    Prev
    Next
    INDEX
    Explanations

    demand for

    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
    æĪĸå¤ļ
    -0.20
    èĢĥãģĪ
    -0.19
    agus
    -0.18
    湯
    -0.18
    APO
    -0.18
    ä»£è¡¨åĽ¢
    -0.18
    çĸ«æĥħå½±åĵį
    -0.18
    ä¸ĢæŃ¥
    -0.18
    abra
    -0.17
    abras
    -0.17
    POSITIVE LOGITS
    éĩı
    0.21
    æĹºçĽĽ
    0.20
    éľĢæ±Ĥ
    0.20
    uset
    0.19
    åĴĮæĶ¯æĮģ
    0.18
     demand
    0.18
    à¹ģละà¸Ħวาม
    0.18
    -facing
    0.18
    æĥħåĨµä¸ĭ
    0.17
    ivative
    0.17
    Activations Density 0.032%

    No Known Activations