© 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. 11838
    Prev
    Next
    INDEX
    Explanations

    slavery or servitude concepts

    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
     taÅŁÄ±
    -0.20
    igh
    -0.19
    绿èī²éĢļéģĵ
    -0.18
    -eyed
    -0.17
    å¸
    -0.17
    ider
    -0.17
     hÃłi
    -0.17
    æĨ¾
    -0.16
    èĢģ人家
    -0.16
    访
    -0.16
    POSITIVE LOGITS
    ä»Ĩ
    0.22
    ordo
    0.21
    (serv
    0.19
    /animate
    0.19
    å½¹
    0.19
    ÑģÑĤв
    0.18
    æĦıè¯Ĩ
    0.18
    ä½£
    0.18
    /master
    0.18
    /helper
    0.18
    Activations Density 0.034%

    No Known Activations