© 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. 12088
    Prev
    Next
    INDEX
    Explanations

    kilometers, kilograms, centimeters, millimeters

    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
     sá»ķ
    -0.19
    еÑģÑĤеÑģÑĤвенн
    -0.18
    индив
    -0.18
    à¸Ħà¸ĵะà¸ģรรม
    -0.18
    CTION
    -0.18
    elo
    -0.18
    индивид
    -0.17
    ÑģлÑĥÑĪа
    -0.17
    seg
    -0.17
    bnb
    -0.17
    POSITIVE LOGITS
    大éĿ¢ç§¯
    0.21
    ogram
    0.20
    ìĶ©
    0.20
    ograms
    0.20
    caps
    0.18
    abytes
    0.18
    ÙĬات
    0.18
    igrams
    0.18
    ophone
    0.18
    æĩ¦
    0.17
    Activations Density 0.023%

    No Known Activations