© 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. 10923
    Prev
    Next
    INDEX
    Explanations

    pan, pen, plate, gel

    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
    cean
    -0.20
    /preferences
    -0.18
    itä
    -0.18
    æĪijçļĦå¿ĥ
    -0.17
    parcel
    -0.17
    åĮħåĮħ
    -0.17
    éĩijåĪļ
    -0.17
    quences
    -0.17
    cych
    -0.17
    æ£Ĥ
    -0.16
    POSITIVE LOGITS
    ama
    0.19
    shm
    0.19
    set
    0.17
    starter
    0.17
    çļĦè¦ģæ±Ĥ
    0.17
    ter
    0.17
    ä¸ĬçļĦ
    0.17
    温度
    0.17
    holders
    0.17
    mates
    0.16
    Activations Density 0.003%

    No Known Activations