© 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. 11205
    Prev
    Next
    INDEX
    Explanations

    plays out

    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
    .getObject
    -0.18
     bá»ı
    -0.18
    ampo
    -0.17
    imes
    -0.16
    娣
    -0.16
    OfYear
    -0.16
    ï¸ı
    -0.16
    æݢ讨
    -0.16
    pytest
    -0.15
    ald
    -0.15
    POSITIVE LOGITS
    累累
    0.21
    丰åİļ
    0.20
    ingly
    0.20
     ($)
    0.18
    èį«
    0.17
    å¤Ļ
    0.17
    èī°å·¨
    0.16
    ÑĤеÑĢ
    0.16
    çĸijæĥij
    0.16
    æľŁåĨħ
    0.16
    Activations Density 0.010%

    No Known Activations