© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12487
    Prev
    Next
    INDEX
    Explanations

    married people and their families

    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
    æķijåĬ©
    -0.21
    管çIJĨå±Ģ
    -0.20
    .stub
    -0.19
    éľĵ
    -0.19
    åįĹæĸ¹
    -0.19
    å°¸
    -0.18
     Stuttgart
    -0.18
    åĶĨ
    -0.18
    eous
    -0.18
    çłĤ
    -0.18
    POSITIVE LOGITS
    /off
    0.19
    çĬ¶æĢģä¸ĭ
    0.19
    iram
    0.18
    anj
    0.18
    embro
    0.18
    /un
    0.18
    uration
    0.18
    iale
    0.18
    ials
    0.17
     cow
    0.17
    Activations Density 0.012%

    No Known Activations