© 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. 11596
    Prev
    Next
    INDEX
    Explanations

    science and research publications

    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
    -Semit
    -0.20
    azon
    -0.20
    pline
    -0.20
     WOW
    -0.19
    ãĥĥãĤ·
    -0.19
    éĩįåŀĭ
    -0.19
     mükem
    -0.18
    ãģ£ãģ¦ãģĬãĤĬãģ¾ãģĻ
    -0.18
    immer
    -0.18
    .simps
    -0.18
    POSITIVE LOGITS
    å¸®ä½ł
    0.22
    adians
    0.20
    å®ļéĩı
    0.20
    ç§ijåŃ¦å®¶
    0.20
     experiment
    0.20
    Science
    0.20
     MIT
    0.20
     science
    0.19
    ç§ijå¹»
    0.19
    _MIX
    0.19
    Activations Density 0.058%

    No Known Activations