© 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. 13654
    Prev
    Next
    INDEX
    Explanations

    dates, cheese, appetisers

    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
    ç«¥è£ħ
    -0.22
    æ·¦
    -0.21
    há»ķ
    -0.21
    æīĢæľīæĥħèĬĤ
    -0.20
    秧
    -0.20
    .getLength
    -0.19
    venth
    -0.19
     Shoes
    -0.19
    indow
    -0.19
    Ctrls
    -0.19
    POSITIVE LOGITS
     appet
    0.27
    éħįä¸Ĭ
    0.23
     attract
    0.21
     наб
    0.21
    æIJŃéħį
    0.21
    æ¡ĮéĿ¢
    0.20
    еÑģÑĤво
    0.20
     gal
    0.19
     board
    0.19
    ãĥľãĥ¼ãĥī
    0.19
    Activations Density 0.016%

    No Known Activations