© 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. 11044
    Prev
    Next
    INDEX
    Explanations

    web usage

    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
    èĢģé¼ł
    -0.25
    gmail
    -0.20
    æīĵåħ¥
    -0.20
    ãĥĹãĥªãĥ³
    -0.19
     distinct
    -0.18
    cek
    -0.18
     Russo
    -0.18
     lump
    -0.17
    -0.17
     traits
    -0.17
    POSITIVE LOGITS
    inars
    0.19
    ãĤ·ãĥ§ãĥĥãĥĹ
    0.19
     Cutter
    0.19
    åħ¬çº¦
    0.19
    ä¿IJ
    0.19
    å·¡åĽŀ
    0.19
    iaux
    0.18
    麸
    0.18
    å©Ĩ
    0.18
     Hij
    0.18
    Activations Density 0.017%

    No Known Activations