© 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. 14020
    Prev
    Next
    INDEX
    Explanations

    coming soon or future events

    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
    åİŁæĿ¥
    -0.21
    GES
    -0.19
    ophilia
    -0.19
    rones
    -0.18
     heaps
    -0.18
    æĿ¥åĽŀ
    -0.18
     Erotische
    -0.18
    åİŁæľīçļĦ
    -0.18
    éĺŁä¼į
    -0.18
    öl
    -0.18
    POSITIVE LOGITS
    ç»ĨåĪĻ
    0.23
    踵
    0.21
    æĻĸ
    0.20
    广åijĬ
    0.20
    ugi
    0.20
    寰
    0.19
    绪
    0.19
    åĺ§
    0.19
    ÙĦØŃ
    0.18
     Durant
    0.18
    Activations Density 0.022%

    No Known Activations