© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11420
    Prev
    Next
    INDEX
    Explanations

    oncolytic virus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    MASTER
    -0.18
    éªIJ
    -0.17
    æݥ纳
    -0.17
    é¸
    -0.17
    _va
    -0.17
    æĭ®
    -0.17
    鸾
    -0.17
    车åŃIJ
    -0.17
    .ends
    -0.17
    /kernel
    -0.17
    POSITIVE LOGITS
    gers
    0.20
    èĭĩ
    0.19
    éĶĢ
    0.19
    iders
    0.19
    idot
    0.19
    UGE
    0.18
    (Void
    0.18
    è¿Ľåº¦
    0.18
    åŃĢ
    0.17
    墨
    0.17
    Activations Density 0.019%

    No Known Activations