© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1034
    Prev
    Next
    INDEX
    Explanations

    contrast agent

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Inflate
    -0.27
    ses
    -0.22
    ç¬ijç¬ij
    -0.21
    質
    -0.21
    ä½ľåĵģåĨħ容
    -0.21
     Officials
    -0.21
     weblog
    -0.20
     #'
    -0.20
     Conway
    -0.20
    .wordpress
    -0.20
    POSITIVE LOGITS
    -like
    0.29
    èİ·å¾ĹäºĨ
    0.25
    .reducer
    0.24
    ä¸Ģæł·çļĦ
    0.23
     (£
    0.23
    -type
    0.23
    ä¸Ģèµ·æĿ¥
    0.23
    ä¸Ģèµ·
    0.22
    -esque
    0.22
    -style
    0.22
    Activations Density 0.070%

    No Known Activations