© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17233
    Prev
    Next
    INDEX
    Explanations

    build environment

    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
    Negative Logits
    semble
    -0.17
    bone
    -0.17
    ending
    -0.17
    ÑĨеп
    -0.17
    -building
    -0.17
    dice
    -0.17
    群ä¼Ĺ
    -0.17
    emb
    -0.16
    Builders
    -0.16
     lẽ
    -0.16
    POSITIVE LOGITS
    ings
    0.20
    rary
    0.19
    åĬŃ
    0.18
    ski
    0.17
    liness
    0.17
    edor
    0.17
    OME
    0.16
    ness
    0.16
    ments
    0.16
    åīįéĶĭ
    0.15
    Activations Density 0.044%

    No Known Activations