© 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. 17123
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    lit
    -0.20
    кла
    -0.20
    reb
    -0.19
    inct
    -0.19
    éºĴ
    -0.18
    çī¯
    -0.18
    åĴ½åĸī
    -0.17
    iff
    -0.17
    ait
    -0.17
    że
    -0.17
    POSITIVE LOGITS
    çīĩ段
    0.23
    òng
    0.21
    段
    0.20
    åĩłåı¥
    0.19
    代çłģ
    0.19
    forces
    0.19
     postal
    0.19
    å°ıçĻ½
    0.18
    CEPT
    0.18
    igos
    0.18
    Activations Density 0.409%

    No Known Activations