© 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. 15466
    Prev
    Next
    INDEX
    Explanations

    hash

    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
    ÑĪив
    -0.17
    媳
    -0.16
    Ñĩе
    -0.15
    å¹ħ
    -0.15
    ationToken
    -0.15
    asts
    -0.15
    çĶŁäº§æĢ»åĢ¼
    -0.15
    à¸Ľà¸ı
    -0.15
    лим
    -0.14
    jsx
    -0.14
    POSITIVE LOGITS
    imoto
    0.23
    0.21
    din
    0.18
    eds
    0.17
     ÐIJлекÑģан
    0.17
    pile
    0.17
    è£Ķ
    0.17
    ierarchy
    0.16
    intosh
    0.16
    pone
    0.16
    Activations Density 0.039%

    No Known Activations