© 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. 13901
    Prev
    Next
    INDEX
    Explanations

    backed by

    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
    ç¢į
    -0.17
    اÙĪر
    -0.17
    Ùħار
    -0.16
    naments
    -0.16
    à¸Ļา
    -0.15
    ritel
    -0.15
     пÑĢоÑĤиво
    -0.15
    uales
    -0.15
    atum
    -0.15
    burgh
    -0.15
    POSITIVE LOGITS
    -up
    0.24
    ðŁı»
    0.22
    /support
    0.21
    less
    0.21
    ðŁı¼
    0.21
    ä¸įä½ı
    0.20
    å¨ĺ
    0.20
    -Up
    0.19
    up
    0.19
    heet
    0.19
    Activations Density 0.008%

    No Known Activations