© 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. 16991
    Prev
    Next
    INDEX
    Explanations

    aggregate and aggregating

    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
    fully
    -0.23
    fulness
    -0.22
    lessness
    -0.19
    ened
    -0.18
    活泼
    -0.17
    lessly
    -0.17
    eger
    -0.17
    ģ
    -0.17
    ward
    -0.17
    atically
    -0.17
    POSITIVE LOGITS
    ordin
    0.18
    ity
    0.18
    Ñīе
    0.18
     Nack
    0.18
    eur
    0.17
    çĹĩ
    0.17
    ção
    0.16
    reate
    0.16
    /com
    0.16
    opt
    0.16
    Activations Density 0.021%

    No Known Activations