© 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. 17226
    Prev
    Next
    INDEX
    Explanations

    focus or attention

    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
    ilon
    -0.23
    DataReader
    -0.22
    imizer
    -0.21
    볨
    -0.21
    .copyOf
    -0.21
    ctxt
    -0.20
    .reducer
    -0.19
    å¾Ĵ
    -0.19
    .UNKNOWN
    -0.19
    iciel
    -0.19
    POSITIVE LOGITS
     range
    0.21
     облаÑģÑĤÑĮ
    0.21
    æľ¦èĥ§
    0.21
    range
    0.19
     coveted
    0.19
    èĮĥåĽ´
    0.19
    èĶ¬
    0.18
     TTL
    0.18
     ranges
    0.18
    åħ¼é¡¾
    0.18
    Activations Density 0.015%

    No Known Activations