© 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. 13389
    Prev
    Next
    INDEX
    Explanations

    @ mentions

    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
    çĨ¬
    -0.21
    fall
    -0.21
    ego
    -0.21
    ä¸Ģ件äºĭ
    -0.20
    çļĦä¸Ģ项
    -0.19
    ç¥
    -0.19
    ookie
    -0.18
    erg
    -0.18
    .jsp
    -0.18
     limp
    -0.18
    POSITIVE LOGITS
    çĵ£
    0.20
    imulator
    0.19
    redients
    0.18
    âľĺ
    0.18
    ä¿Ŀ驾æĬ¤
    0.17
    enaries
    0.17
    æĹłå£°
    0.17
     Ir
    0.17
    Ir
    0.17
    äºĭåıij
    0.17
    Activations Density 0.020%

    No Known Activations