© 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. 16427
    Prev
    Next
    INDEX
    Explanations

    geographical regions

    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
    该æĿij
    -0.21
    è±ģ
    -0.20
    (href
    -0.20
     villagers
    -0.19
     village
    -0.19
    åįĩ
    -0.19
    åij¨æģ©æĿ¥
    -0.18
    顽强
    -0.18
    bers
    -0.18
    åħ¨æĿij
    -0.18
    POSITIVE LOGITS
    æľ¬åľŁ
    0.20
     ÑģÑĤаÑĢ
    0.20
    çļĦèĢģ
    0.19
    RAFT
    0.19
    åĨ¤
    0.18
    尾巴
    0.18
    åħ±æĮ¯
    0.18
    轸
    0.18
     BI
    0.18
    干线
    0.18
    Activations Density 0.335%

    No Known Activations