© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2493
    Prev
    Next
    INDEX
    Explanations

    if ... then

    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
    ãĤĤãģ®ãģ®
    -0.24
    ç»
    -0.23
    å°ıå°ıçļĦ
    -0.23
    渤
    -0.22
     Quite
    -0.22
    大大å°ıå°ı
    -0.21
    afia
    -0.21
    大大å°ı
    -0.21
    ç´ĭ
    -0.21
    unning
    -0.21
    POSITIVE LOGITS
    çļĦè¯Ŀ
    0.28
     univers
    0.26
     would
    0.25
    就好äºĨ
    0.25
    ç¼Ł
    0.24
     hät
    0.24
     had
    0.24
     mere
    0.23
    寻常
    0.23
     hadn
    0.23
    Activations Density 0.042%

    No Known Activations