© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3287
    Prev
    Next
    INDEX
    Explanations

    (Photo credit:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ThanOrEqualTo
    -0.23
    põe
    -0.23
    DisplayStyle
    -0.23
    EMENT
    -0.22
    rowse
    -0.22
    é«ĺçŃīæķĻèĤ²
    -0.22
    ecessary
    -0.22
    竹
    -0.21
    çı
    -0.21
    çľŁäºº
    -0.21
    POSITIVE LOGITS
     Hum
    0.22
     lunches
    0.22
    ä¼ĺç¾İ
    0.22
     Lightweight
    0.22
    uniq
    0.22
    :
    0.22
     genius
    0.21
    all
    0.21
     ventil
    0.21
    unes
    0.21
    Activations Density 0.004%

    No Known Activations