© 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. 228
    Prev
    Next
    INDEX
    Explanations

    Activity, Guest, Calendar

    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
    æķ£
    -0.23
    /from
    -0.23
    æ²Ļé¾Ļ
    -0.23
    æĻ®åıĬ
    -0.21
    iasco
    -0.21
    zend
    -0.21
    _blk
    -0.21
     specifically
    -0.21
    celand
    -0.21
    ournals
    -0.21
    POSITIVE LOGITS
    ikk
    0.27
     Viewing
    0.23
    èݽ
    0.23
    Crystal
    0.23
    Corner
    0.23
     Seen
    0.23
     viewing
    0.23
    认为
    0.22
    æ¡Ģ
    0.22
    seen
    0.22
    Activations Density 0.001%

    No Known Activations