© 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. 11779
    Prev
    Next
    INDEX
    Explanations

    Universal Permissive License UPL

    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
    OrUpdate
    -0.23
    onda
    -0.19
    acre
    -0.18
    lor
    -0.18
    iaux
    -0.18
    hawk
    -0.17
    è¾±
    -0.17
    Ñĥж
    -0.16
    çĦ±
    -0.16
    ching
    -0.15
    POSITIVE LOGITS
    psilon
    0.20
    /down
    0.20
    ILITY
    0.20
    itarian
    0.19
    ilities
    0.18
    aub
    0.17
    ÑĤÑĢен
    0.17
    ÑĤвоÑĢ
    0.17
    aviolet
    0.16
    صر
    0.16
    Activations Density 0.515%

    No Known Activations