© 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. 10389
    Prev
    Next
    INDEX
    Explanations

    `[` or `(` enclosure

    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
    ires
    -0.20
    hue
    -0.18
    ãĥ¼ãĤ·
    -0.18
    sWith
    -0.17
    ein
    -0.17
    tas
    -0.17
    ação
    -0.17
    fade
    -0.17
    others
    -0.17
     THAN
    -0.17
    POSITIVE LOGITS
    ting
    0.20
    nya
    0.18
    nn
    0.17
     (
    0.17
    bove
    0.16
    åĭĩ士
    0.16
    tempts
    0.16
    å¹Ħ
    0.16
    ervice
    0.16
    ged
    0.16
    Activations Density 0.149%

    No Known Activations