© 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. 11221
    Prev
    Next
    INDEX
    Explanations

    balcony, night, encore

    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
    ä»Ģä¹Īåij¢
    -0.20
    tpl
    -0.20
    èĩ§
    -0.19
    çIJĨ
    -0.19
    виÑĤ
    -0.18
    çķ´
    -0.18
    忽
    -0.17
     gradient
    -0.17
     Compiled
    -0.17
     impact
    -0.17
    POSITIVE LOGITS
    çĵ®
    0.19
    æĺ¯æĪijåĽ½
    0.19
    ç©¿ä¸Ĭ
    0.18
    飫
    0.18
    西è£ħ
    0.18
    亿ä¸ĩ
    0.18
    jÄħ
    0.18
     Prime
    0.18
    ForRow
    0.18
    çĶ©
    0.18
    Activations Density 0.001%

    No Known Activations