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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 244
    Prev
    Next
    INDEX
    Explanations

    Intel, discrete, CPU, graphics

    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
    éŀŃ
    -0.24
    沧æ¡ij
    -0.24
    æĻŁ
    -0.23
    åħĨ
    -0.23
    gn
    -0.22
    ulen
    -0.22
    社ä¼ļæķĪçĽĬ
    -0.22
    gst
    -0.22
    ä¸ĩåı°
    -0.22
    blings
    -0.21
    POSITIVE LOGITS
     family
    0.26
     four
    0.25
     superior
    0.24
     Premium
    0.23
     premium
    0.23
     upper
    0.23
     Profiles
    0.22
    家æĹı
    0.22
     suite
    0.22
    encode
    0.22
    Activations Density 0.005%

    No Known Activations