© 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. 10567
    Prev
    Next
    INDEX
    Explanations

    made available under

    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
    éĽª
    -0.20
    esen
    -0.18
     cher
    -0.18
    次ä¼ļè®®
    -0.18
    å®Įç¾İ
    -0.18
    ypress
    -0.17
    .Buffered
    -0.17
    .hu
    -0.17
    ä»°
    -0.17
    .Tx
    -0.17
    POSITIVE LOGITS
     availability
    0.42
     доÑģÑĤÑĥп
    0.41
     available
    0.40
    .available
    0.35
    åı¯çĶ¨
    0.35
    available
    0.34
     accessible
    0.33
     access
    0.33
    availability
    0.33
    accessible
    0.32
    Activations Density 0.160%

    No Known Activations