© 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. 1690
    Prev
    Next
    INDEX
    Explanations

    .dom, .Security, REGISTER, Baseline

    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
    URT
    -0.27
    icorn
    -0.23
    _TOO
    -0.23
    inson
    -0.23
    ÃŃg
    -0.22
    èł¡
    -0.22
    oton
    -0.22
    ché
    -0.21
    irt
    -0.21
    wal
    -0.21
    POSITIVE LOGITS
    æľºçĶµ
    0.24
    社ä¼ļç»Ħç»ĩ
    0.23
    éĽ¨æ°´
    0.23
    åªĴä»ĭ
    0.23
     observ
    0.23
    æĮł
    0.23
    åŁİ乡
    0.21
    REGISTER
    0.21
    Baseline
    0.21
    æĺī
    0.21
    Activations Density 0.074%

    No Known Activations