© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14951
    Prev
    Next
    INDEX
    Explanations

    deciduous or hardwood

    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
     pct
    -0.18
     Wheat
    -0.18
    å¾Ģå¤ĸ
    -0.17
    orage
    -0.17
    "fmt
    -0.17
    etto
    -0.17
    hw
    -0.16
    å·¥åľ°
    -0.16
     distinct
    -0.16
    ruit
    -0.16
    POSITIVE LOGITS
    们
    0.29
    çijĻ
    0.22
    acre
    0.22
    们éĥ½
    0.19
    åIJįå½ķ
    0.19
    ansa
    0.19
    ieee
    0.18
    sd
    0.18
    кÑĢо
    0.18
    iers
    0.18
    Activations Density 0.003%

    No Known Activations