© 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. 12040
    Prev
    Next
    INDEX
    Explanations

    close or barely winning

    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
    è·³èĪŀ
    -0.20
    è¿ĻåĿĹ
    -0.20
    å¾¹
    -0.20
    _OPTS
    -0.19
    ç¥ĸ
    -0.19
     skipped
    -0.18
    endum
    -0.18
    æĸ¹ä¾¿
    -0.18
    аÑĢам
    -0.17
    Ñīи
    -0.17
    POSITIVE LOGITS
    æĮ½
    0.26
    BLE
    0.21
     victory
    0.20
    樯
    0.20
    tras
    0.19
    ly
    0.19
     barely
    0.18
    èİ·èĥľ
    0.18
    coe
    0.18
    ily
    0.18
    Activations Density 0.014%

    No Known Activations