© 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. 15949
    Prev
    Next
    INDEX
    Explanations

    children's

    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
    gn
    -0.21
    day
    -0.18
    tees
    -0.17
    itude
    -0.17
    индив
    -0.17
    индивид
    -0.16
    åľ°çĤ¹
    -0.15
    TestCategory
    -0.15
    uffers
    -0.15
    pir
    -0.15
    POSITIVE LOGITS
    hood
    0.27
    媳
    0.22
    ÑĪки
    0.22
    esis
    0.20
    zimmer
    0.19
    åĢij
    0.18
    ishly
    0.17
    bearing
    0.17
    ÑĪек
    0.17
    оз
    0.16
    Activations Density 0.082%

    No Known Activations