© 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. 10609
    Prev
    Next
    INDEX
    Explanations

    media query

    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
    ses
    -0.22
    ths
    -0.22
    /her
    -0.19
    shine
    -0.19
    ored
    -0.18
    sk
    -0.17
    ÑģÑı
    -0.17
    ton
    -0.17
    mul
    -0.17
    meal
    -0.17
    POSITIVE LOGITS
    å·¥ä½ľèĢħ
    0.18
    å¦ģ
    0.17
    ä¼ī
    0.17
    hift
    0.16
    itet
    0.16
    ÙĬدÙĬ
    0.16
    KHR
    0.16
    illon
    0.15
    lectic
    0.15
    ะ
    0.15
    Activations Density 0.034%

    No Known Activations