© 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. 14689
    Prev
    Next
    INDEX
    Explanations

    SDK context

    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
    ood
    -0.21
     retro
    -0.20
    åĬĽè¿ĺæĺ¯
    -0.20
    nim
    -0.19
    lessly
    -0.19
    eka
    -0.18
     asc
    -0.18
    纶
    -0.18
    sters
    -0.18
    åĬĪ
    -0.17
    POSITIVE LOGITS
    éŨè¯Ĭ
    0.19
    enton
    0.19
    pell
    0.19
    éĺ²çĽĹ
    0.18
    åºĵ
    0.18
    culator
    0.18
    entes
    0.17
    yun
    0.17
    éħįåIJĪ
    0.17
    plug
    0.17
    Activations Density 0.045%

    No Known Activations