© 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. 14747
    Prev
    Next
    INDEX
    Explanations

    iridescent, iation, angioedema

    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
    oggle
    -0.18
    į
    -0.17
    æѤåĪ»
    -0.17
    æ°¨éħ¸
    -0.16
    elper
    -0.16
     sứ
    -0.15
    wear
    -0.15
    ÑĮÑı
    -0.15
    èĭĵ
    -0.15
    atts
    -0.15
    POSITIVE LOGITS
    eous
    0.21
    eer
    0.21
    stra
    0.20
    ein
    0.20
    omic
    0.18
    ej
    0.17
    ech
    0.17
    ean
    0.17
    osh
    0.17
    iej
    0.17
    Activations Density 0.004%

    No Known Activations