© 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. 15773
    Prev
    Next
    INDEX
    Explanations

    urls with specific domains

    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
    åŁİåİ¿
    -0.19
    åīįä»»
    -0.19
    çĿ¨
    -0.18
    umer
    -0.18
    ç·
    -0.18
    é¦ĸé¢Ĩ
    -0.18
    orsi
    -0.17
     bölümü
    -0.17
    istring
    -0.16
    andel
    -0.16
    POSITIVE LOGITS
    转æĬĺ
    0.19
    âIJ£
    0.18
     Weekend
    0.18
    纡
    0.18
    sand
    0.18
    fans
    0.17
    onth
    0.17
    mind
    0.17
    éĻħ
    0.17
    -archive
    0.17
    Activations Density 0.098%

    No Known Activations