© 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. 14401
    Prev
    Next
    INDEX
    Explanations

    file extensions

    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
    MSN
    -0.20
    çĽ¾
    -0.19
    èĻIJ
    -0.18
    èĬľ
    -0.18
    سÙģ
    -0.18
     üz
    -0.18
    å¼ĺæī¬
    -0.17
    ddit
    -0.17
    飧
    -0.17
    æĬ¤å£«
    -0.17
    POSITIVE LOGITS
    .tc
    0.19
     bell
    0.18
    橱
    0.18
     dib
    0.17
    ç©·
    0.17
    .sigmoid
    0.17
    浪潮
    0.17
     manh
    0.17
     Dexter
    0.17
    为æĬĵ
    0.17
    Activations Density 0.027%

    No Known Activations