© 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. 2345
    Prev
    Next
    INDEX
    Explanations

    with [number/quantity/condition]

    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
     Broadcasting
    -0.23
     Widow
    -0.23
    快讯
    -0.23
     ØŃÙĬÙĨ
    -0.22
    æľīæĦıæĢĿçļĦ
    -0.22
    _rp
    -0.22
     MUST
    -0.21
    åĽłä¸ºå¥¹
    -0.21
    sted
    -0.21
    omit
    -0.21
    POSITIVE LOGITS
    è¿Ļä¹Īå¤ļ
    0.30
    ä¸įæĸŃ
    0.29
    çľĭæĿ¥
    0.29
    ä¸įæĸŃçļĦ
    0.29
    æĹ¥çĽĬ
    0.29
     hindsight
    0.28
    å®Į
    0.27
    å¦Ĥä»Ĭ
    0.27
    drawing
    0.27
    å¦ĤæѤ
    0.27
    Activations Density 0.124%

    No Known Activations