© 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. 10397
    Prev
    Next
    INDEX
    Explanations

    arena

    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
    ening
    -0.26
    ened
    -0.24
    ãģĹãģ¾ãģĨ
    -0.24
    çīĸ
    -0.20
    ãģĹãģ¾
    -0.20
    ãģĹãģ¾ãģĦ
    -0.19
    aries
    -0.18
    enticator
    -0.17
    onomy
    -0.17
    iously
    -0.17
    POSITIVE LOGITS
    åĨħçļĦ
    0.23
    mit
    0.18
    -wide
    0.18
    人士
    0.17
    throp
    0.17
    ize
    0.16
    ockey
    0.16
    大
    0.15
    ault
    0.15
    nable
    0.15
    Activations Density 0.007%

    No Known Activations