© 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. 11898
    Prev
    Next
    INDEX
    Explanations

    within [number]

    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
    ëĭ¹
    -0.20
    èĨ¨èĥĢ
    -0.20
     bÃło
    -0.19
    çĽĶ
    -0.19
     getLogger
    -0.18
    Å¡t
    -0.18
    ç±³é¥Ń
    -0.18
    æħ¢æħ¢çļĦ
    -0.18
    ä¸į幸
    -0.18
     Mish
    -0.18
    POSITIVE LOGITS
    CurrentValue
    0.22
     знаÑĩениÑı
    0.20
    åĢ
    0.20
    weg
    0.19
    CAC
    0.18
    egas
    0.17
    ä¸Ģåij³
    0.17
    iphy
    0.17
    ä¸Ģåı¥è¯Ŀ
    0.17
    ogen
    0.17
    Activations Density 0.002%

    No Known Activations