© 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. 16154
    Prev
    Next
    INDEX
    Explanations

    miles, acre, feet, thousands, types, custom

    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
    Disposed
    -0.21
    å®ļéĩı
    -0.20
     uLocal
    -0.19
    oplast
    -0.19
     priced
    -0.19
    å¯Ħæīĺ
    -0.19
    èĭ¥å¹²
    -0.19
    ÄĻp
    -0.18
    apult
    -0.18
     Subset
    -0.18
    POSITIVE LOGITS
    ç§įç±»
    0.29
    ä¸ĥ大
    0.23
    å¤ļ个
    0.23
    å®ĮåĸĦçļĦ
    0.22
    ç²¾å¿ĥ
    0.21
    çݯç»ķ
    0.21
    çĭ¬çī¹çļĦ
    0.21
    инд
    0.20
    æ·¡
    0.20
    immer
    0.20
    Activations Density 0.021%

    No Known Activations