© 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. 15421
    Prev
    Next
    INDEX
    Explanations

    silver, wood, china, gold, 8

    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
    oning
    -0.19
    Bins
    -0.18
     Dias
    -0.18
    èĽŃ
    -0.17
    寥
    -0.17
    åħĪåIJİ
    -0.17
     Flowers
    -0.17
    大å±Ģ
    -0.17
     tact
    -0.17
    å®ģ
    -0.17
    POSITIVE LOGITS
    éĴ
    0.22
    çŃī级
    0.19
    人å±ħ
    0.18
    éĻ¤æѤ
    0.17
    ãģıãĤĭ
    0.17
    tur
    0.17
    éĩijèī²
    0.17
    éĶĶ
    0.17
    çī¹æ´¾
    0.17
    /misc
    0.17
    Activations Density 0.004%

    No Known Activations