© 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. 16648
    Prev
    Next
    INDEX
    Explanations

    months and 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
    иÑĤели
    -0.19
    çģ¯ç¬¼
    -0.19
    亲çĪ±
    -0.19
    度
    -0.18
    èĥĦ
    -0.18
    ä½ĵç³»
    -0.18
    è¿Ļæł·åģļ
    -0.18
     neuken
    -0.18
    UME
    -0.18
    rium
    -0.17
    POSITIVE LOGITS
    为主çļĦ
    0.24
    举è¡ĮçļĦ
    0.21
    è§Ħå®ļçļĦ
    0.21
     tran
    0.20
    å·²ä¹ħçļĦ
    0.19
    彦
    0.19
     block
    0.19
    avored
    0.19
    å½¢æĪIJçļĦ
    0.19
    ç»ĦæĪIJçļĦ
    0.19
    Activations Density 0.057%

    No Known Activations