© 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. 16155
    Prev
    Next
    INDEX
    Explanations

    glacier, ice, ocean, temperature, Arctic

    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
     Formal
    -0.22
    æī§ä¸ļ
    -0.22
    благо
    -0.21
    å¹ķ
    -0.21
    ä¸į便
    -0.20
    panies
    -0.20
     raÄŁ
    -0.20
    ãĥĽãĥĨ
    -0.19
    å§Ķç»Ħç»ĩéĥ¨
    -0.19
     formal
    -0.19
    POSITIVE LOGITS
     ocean
    0.25
     ice
    0.24
    åĨ°
    0.24
    æµĭéĩı
    0.23
    æ°´éĩı
    0.23
     measurements
    0.23
    èŀįåĮĸ
    0.22
    Ice
    0.22
    mel
    0.22
    æľĢå¿«çļĦ
    0.22
    Activations Density 0.046%

    No Known Activations