© 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. 16028
    Prev
    Next
    INDEX
    Explanations

    SQL table definitions

    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
    lich
    -0.21
    Vir
    -0.20
     Vir
    -0.19
    ussion
    -0.19
    _COLORS
    -0.19
    æĺİåªļ
    -0.19
    bsite
    -0.18
    èĮ´
    -0.18
    符åı·
    -0.18
     vir
    -0.18
    POSITIVE LOGITS
    Stan
    0.22
     Sioux
    0.20
    aniem
    0.20
    è¶ĭ
    0.19
    两岸
    0.18
    éŀį
    0.17
    ä¸ĥæĺŁ
    0.17
    績
    0.17
    ivant
    0.17
     Stanley
    0.17
    Activations Density 0.001%

    No Known Activations